{ "metadata": { "total_size": 31446785024 }, "weight_map": { "lm_head.weight": "model-00007-of-00007.safetensors", "model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.10.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.10.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.11.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.11.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.12.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.12.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.13.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.13.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.14.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.15.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.15.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.16.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.16.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.17.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.17.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.18.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.18.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.19.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.19.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.20.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.20.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.21.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.21.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.22.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.22.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.23.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.23.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.24.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.24.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.25.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.25.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.26.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.26.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.27.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.27.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.28.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.28.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.29.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.29.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.30.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.30.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.31.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.31.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.32.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.33.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.34.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.35.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.36.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.37.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.38.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.39.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.4.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.4.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.40.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.41.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.42.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.43.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.44.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.45.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.46.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.48.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.49.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.5.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.5.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.50.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.51.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.52.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.53.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.54.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.55.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.56.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.57.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.59.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.6.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.6.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.60.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.60.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.61.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.61.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.62.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.62.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.63.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.63.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.7.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.7.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.8.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.8.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.9.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.experts.9.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.gate.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.kv_b_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.0.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.0.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.1.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.1.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.10.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.10.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.11.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.11.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.12.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.12.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.13.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.13.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.14.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.14.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.15.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.15.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.16.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.16.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.17.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.17.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.18.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.18.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.19.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.19.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.2.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.2.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.20.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.20.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.21.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.21.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.22.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.22.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.23.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.23.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.24.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.24.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.25.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.25.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.26.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.26.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.27.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.27.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.28.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.28.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.29.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.29.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.3.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.3.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.30.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.30.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.31.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.31.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.32.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.32.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.33.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.33.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.34.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.34.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.35.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.35.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.36.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.36.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.37.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.37.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.38.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.38.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.39.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.39.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.4.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.4.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.40.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.40.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.41.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.41.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.42.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.42.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.43.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.43.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.44.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.44.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.45.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.45.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.46.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.46.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.47.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.47.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.48.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.48.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.49.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.49.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.5.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.5.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.50.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.50.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.51.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.51.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.52.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.52.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.53.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.53.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.54.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.54.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.55.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.55.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.56.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.56.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.57.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.57.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.58.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.58.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.59.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.59.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.6.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.6.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.60.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.60.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.61.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.61.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.62.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.62.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.63.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.63.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.7.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.7.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.8.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.8.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.9.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.experts.9.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.gate.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.kv_b_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.0.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.0.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.1.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.1.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.10.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.10.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.11.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.11.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.12.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.12.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.13.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.13.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.14.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.14.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.15.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.15.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.16.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.16.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.17.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.17.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.18.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.18.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.19.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.19.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.2.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.2.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.20.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.20.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.21.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.21.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.22.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.22.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.23.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.23.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.24.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.24.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.25.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.25.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.26.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.26.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.27.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.27.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.28.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.28.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.29.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.29.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.3.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.3.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.30.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.30.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.31.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.31.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.32.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.32.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.33.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.33.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.34.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.34.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.35.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.35.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.36.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.36.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.37.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.37.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.38.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.38.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.39.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.39.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.4.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.4.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.40.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.40.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.41.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.41.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.42.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.42.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.43.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.43.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.44.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.44.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.45.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.45.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.46.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.46.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.47.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.47.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.48.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.48.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.49.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.49.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.5.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.5.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.50.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.50.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.51.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.51.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.52.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.52.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.53.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.53.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.54.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.54.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.55.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.55.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.56.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.56.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.57.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.57.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.58.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.58.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.59.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.59.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.6.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.6.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.60.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.60.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.61.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.61.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.62.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.62.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.63.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.63.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.7.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.7.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.8.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.8.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.9.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.experts.9.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.gate.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.kv_b_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.0.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.0.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.1.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.1.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.10.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.10.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.11.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.11.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.12.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.12.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.13.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.13.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.14.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.14.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.15.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.15.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.16.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.16.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.17.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.17.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.18.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.18.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.19.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.19.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.2.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.2.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.20.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.20.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.21.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.21.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.22.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.22.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.23.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.23.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.24.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.24.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.25.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.25.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.26.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.26.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.27.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.27.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.28.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.28.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.29.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.29.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.3.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.3.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.30.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.30.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.31.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.31.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.32.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.32.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.33.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.33.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.34.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.34.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.35.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.35.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.36.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.36.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.37.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.37.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.38.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.38.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.39.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.39.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.4.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.4.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.40.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.40.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.41.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.41.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.42.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.42.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.43.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.43.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.44.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.44.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.45.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.45.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.46.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.46.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.47.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.47.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.48.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.48.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.49.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.49.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.5.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.5.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.50.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.50.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.51.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.51.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.52.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.52.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.53.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.53.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.54.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.54.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.55.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.55.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.56.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.56.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.57.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.57.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.58.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.58.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.59.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.59.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.6.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.6.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.60.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.60.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.61.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.61.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.62.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.62.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.63.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.63.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.7.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.7.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.8.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.8.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.9.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.experts.9.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.gate.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.kv_b_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.0.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.0.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.1.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.1.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.10.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.10.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.11.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.11.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.12.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.12.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.13.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.13.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.14.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.14.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.15.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.15.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.16.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.16.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.17.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.17.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.18.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.18.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.19.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.19.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.2.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.2.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.20.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.20.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.21.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.21.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.22.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.22.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.23.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.23.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.24.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.24.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.25.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.25.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.26.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.26.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.27.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.27.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.28.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.28.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.29.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.29.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.3.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.3.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.30.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.30.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.31.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.31.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.32.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.32.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.33.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.33.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.34.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.34.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.35.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.35.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.36.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.36.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.37.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.37.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.38.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.38.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.39.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.39.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.4.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.4.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.40.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.40.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.41.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.41.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.42.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.42.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.43.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.43.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.44.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.44.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.45.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.45.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.46.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.46.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.47.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.47.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.48.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.48.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.49.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.49.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.5.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.5.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.50.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.50.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.51.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.51.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.52.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.52.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.53.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.53.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.54.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.54.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.55.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.55.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.56.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.56.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.57.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.57.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.58.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.58.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.59.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.59.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.6.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.6.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.60.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.60.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.61.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.61.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.62.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.62.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.63.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.63.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.experts.7.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.7.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.8.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.8.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.9.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.experts.9.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.mlp.gate.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.13.self_attn.kv_a_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.kv_b_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.0.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.0.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.1.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.1.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.10.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.10.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.11.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.11.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.12.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.12.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.13.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.13.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.14.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.14.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.15.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.15.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.16.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.16.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.17.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.17.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.18.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.18.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.19.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.19.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.2.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.2.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.20.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.20.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.21.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.21.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.22.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.22.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.23.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.23.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.24.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.24.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.25.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.25.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.26.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.26.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.27.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.27.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.28.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.28.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.29.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.29.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.3.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.3.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.30.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.30.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.31.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.31.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.32.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.32.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.33.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.33.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.34.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.34.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.35.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.35.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.36.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.36.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.37.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.37.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.38.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.38.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.39.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.39.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.4.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.4.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.40.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.40.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.41.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.41.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.42.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.42.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.43.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.43.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.44.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.44.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.45.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.45.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.46.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.46.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.47.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.47.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.48.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.48.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.49.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.49.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.5.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.5.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.50.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.50.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.51.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.51.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.52.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.52.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.53.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.53.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.54.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.54.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.55.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.55.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.56.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.56.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.57.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.57.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.58.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.58.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.59.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.59.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.6.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.6.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.60.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.60.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.61.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.61.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.62.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.62.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.63.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.63.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.7.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.7.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.8.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.8.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.9.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.experts.9.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.gate.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.kv_b_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.0.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.0.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.1.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.1.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.10.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.10.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.11.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.11.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.12.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.12.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.13.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.13.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.14.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.14.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.15.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.15.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.16.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.16.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.17.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.17.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.18.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.18.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.19.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.19.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.2.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.2.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.20.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.20.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.21.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.21.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.22.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.22.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.23.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.23.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.24.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.24.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.25.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.25.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.26.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.26.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.27.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.27.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.28.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.28.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.29.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.29.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.3.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.3.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.30.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.30.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.31.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.31.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.32.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.32.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.33.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.33.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.34.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.34.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.35.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.35.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.36.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.36.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.37.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.37.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.38.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.38.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.39.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.39.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.4.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.4.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.40.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.40.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.41.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.41.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.42.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.42.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.43.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.43.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.44.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.44.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.45.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.45.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.46.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.46.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.47.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.47.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.48.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.48.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.49.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.49.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.5.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.5.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.50.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.50.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.51.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.51.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.52.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.52.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.53.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.53.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.54.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.54.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.55.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.55.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.56.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.56.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.57.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.57.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.58.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.58.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.59.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.59.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.6.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.6.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.60.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.60.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.61.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.61.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.62.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.62.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.63.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.63.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.7.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.7.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.8.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.8.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.9.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.experts.9.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.gate.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.kv_b_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.0.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.0.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.1.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.1.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.10.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.10.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.11.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.11.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.12.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.12.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.13.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.13.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.14.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.14.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.15.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.15.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.16.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.16.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.17.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.17.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.18.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.18.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.19.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.19.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.2.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.2.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.20.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.20.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.21.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.21.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.22.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.22.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.23.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.23.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.24.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.24.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.25.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.25.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.26.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.26.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.27.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.27.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.28.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.28.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.29.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.29.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.3.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.3.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.30.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.30.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.31.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.31.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.32.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.32.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.33.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.33.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.34.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.34.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.35.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.35.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.36.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.36.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.37.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.37.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.38.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.38.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.39.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.39.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.4.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.4.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.40.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.40.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.41.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.41.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.42.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.42.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.43.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.43.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.44.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.44.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.45.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.45.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.46.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.46.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.47.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.47.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.48.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.48.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.49.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.49.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.5.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.5.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.50.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.50.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.51.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.51.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.52.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.52.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.53.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.53.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.54.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.54.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.55.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.55.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.56.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.56.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.57.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.57.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.58.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.58.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.59.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.59.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.6.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.6.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.60.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.60.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.61.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.61.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.62.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.62.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.63.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.63.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.7.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.7.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.8.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.8.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.9.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.experts.9.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.gate.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.kv_b_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.0.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.0.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.1.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.1.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.10.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.10.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.11.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.11.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.12.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.12.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.13.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.13.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.14.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.14.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.15.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.15.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.16.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.16.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.17.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.17.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.18.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.18.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.19.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.19.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.2.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.2.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.20.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.20.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.21.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.21.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.22.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.22.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.23.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.23.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.24.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.24.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.25.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.25.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.26.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.26.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.27.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.27.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.28.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.28.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.29.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.29.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.3.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.3.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.30.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.30.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.31.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.31.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.32.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.32.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.33.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.33.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.34.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.34.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.35.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.35.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.36.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.36.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.37.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.37.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.38.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.38.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.39.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.39.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.4.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.4.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.40.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.40.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.41.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.41.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.42.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.42.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.43.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.43.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.44.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.44.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.45.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.45.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.46.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.46.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.47.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.47.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.48.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.48.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.49.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.49.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.5.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.5.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.50.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.50.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.51.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.51.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.52.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.52.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.53.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.53.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.54.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.54.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.55.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.55.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.56.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.56.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.57.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.57.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.58.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.58.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.59.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.59.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.6.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.6.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.60.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.60.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.61.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.61.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.62.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.62.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.63.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.63.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.experts.7.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.7.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.8.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.8.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.9.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.experts.9.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.mlp.gate.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.17.self_attn.kv_a_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.kv_b_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.0.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.0.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.1.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.1.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.10.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.10.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.11.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.11.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.12.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.12.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.13.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.13.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.14.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.14.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.15.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.15.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.16.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.16.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.17.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.17.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.18.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.18.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.19.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.19.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.2.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.2.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.20.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.20.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.21.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.21.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.22.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.22.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.23.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.23.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.24.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.24.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.25.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.25.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.26.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.26.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.27.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.27.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.28.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.28.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.29.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.29.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.3.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.3.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.30.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.30.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.31.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.31.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.32.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.32.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.33.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.33.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.34.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.34.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.35.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.35.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.36.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.36.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.37.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.37.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.38.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.38.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.39.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.39.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.4.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.4.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.40.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.40.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.41.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.41.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.42.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.42.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.43.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.43.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.44.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.44.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.45.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.45.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.46.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.46.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.47.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.47.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.48.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.48.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.49.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.49.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.5.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.5.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.50.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.50.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.51.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.51.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.52.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.52.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.53.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.53.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.54.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.54.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.55.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.55.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.56.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.56.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.57.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.57.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.58.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.58.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.59.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.59.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.6.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.6.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.60.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.60.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.61.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.61.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.62.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.62.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.63.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.63.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.7.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.7.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.8.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.8.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.9.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.experts.9.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.gate.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.kv_b_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.0.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.0.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.1.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.1.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.10.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.10.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.11.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.11.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.12.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.12.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.13.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.13.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.14.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.14.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.15.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.15.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.16.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.16.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.17.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.17.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.18.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.18.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.19.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.19.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.2.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.2.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.20.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.20.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.21.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.21.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.22.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.22.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.23.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.23.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.24.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.24.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.25.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.25.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.26.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.26.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.27.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.27.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.28.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.28.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.29.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.29.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.3.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.3.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.30.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.30.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.31.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.31.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.32.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.32.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.33.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.33.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.34.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.34.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.35.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.35.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.36.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.36.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.37.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.37.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.38.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.38.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.39.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.39.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.4.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.4.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.40.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.40.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.41.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.41.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.42.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.42.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.43.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.43.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.44.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.44.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.45.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.45.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.46.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.46.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.47.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.47.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.48.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.48.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.49.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.49.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.5.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.5.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.50.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.50.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.51.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.51.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.52.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.52.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.53.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.53.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.54.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.54.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.55.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.55.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.56.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.56.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.57.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.57.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.58.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.58.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.59.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.59.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.6.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.6.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.60.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.60.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.61.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.61.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.62.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.62.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.63.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.63.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.7.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.7.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.8.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.8.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.9.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.experts.9.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.gate.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.kv_b_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.0.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.0.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.1.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.1.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.10.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.10.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.11.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.11.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.12.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.12.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.13.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.13.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.14.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.14.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.15.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.15.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.16.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.16.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.17.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.17.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.18.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.18.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.19.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.19.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.2.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.2.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.20.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.20.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.21.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.21.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.22.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.22.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.23.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.23.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.24.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.24.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.25.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.25.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.26.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.26.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.27.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.27.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.28.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.28.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.29.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.29.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.3.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.3.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.30.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.30.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.31.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.31.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.32.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.32.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.33.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.33.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.34.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.34.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.35.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.35.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.36.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.36.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.37.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.37.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.38.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.38.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.39.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.39.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.4.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.4.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.40.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.40.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.41.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.41.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.42.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.42.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.43.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.43.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.44.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.44.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.45.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.45.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.46.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.46.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.47.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.47.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.48.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.48.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.49.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.49.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.5.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.5.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.50.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.50.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.51.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.51.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.52.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.52.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.53.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.53.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.54.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.54.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.55.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.55.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.56.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.56.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.57.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.57.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.58.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.58.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.59.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.59.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.6.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.6.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.60.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.60.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.61.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.61.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.62.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.62.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.63.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.63.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.7.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.7.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.8.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.8.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.9.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.experts.9.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.gate.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.kv_b_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.0.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.0.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.1.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.1.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.10.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.10.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.11.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.11.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.12.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.12.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.13.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.13.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.14.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.14.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.15.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.15.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.16.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.16.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.17.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.17.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.18.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.18.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.19.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.19.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.2.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.2.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.20.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.20.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.21.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.21.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.22.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.22.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.23.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.23.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.24.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.24.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.25.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.25.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.26.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.26.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.27.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.27.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.28.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.28.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.29.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.29.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.3.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.3.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.30.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.30.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.31.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.31.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.32.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.32.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.33.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.33.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.34.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.34.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.35.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.35.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.36.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.36.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.37.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.37.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.38.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.38.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.39.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.39.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.4.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.4.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.40.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.40.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.41.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.41.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.42.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.42.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.43.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.43.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.44.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.44.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.45.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.45.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.46.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.46.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.47.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.47.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.48.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.48.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.49.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.49.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.5.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.5.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.50.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.50.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.51.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.51.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.52.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.52.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.53.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.53.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.54.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.54.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.55.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.55.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.56.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.56.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.57.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.57.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.58.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.58.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.59.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.59.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.6.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.6.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.60.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.60.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.61.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.61.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.62.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.62.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.63.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.63.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.7.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.7.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.8.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.8.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.9.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.experts.9.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.gate.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.kv_b_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.0.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.0.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.1.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.1.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.10.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.10.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.11.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.11.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.12.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.12.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.13.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.13.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.14.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.14.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.15.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.15.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.16.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.16.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.17.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.17.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.18.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.18.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.19.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.19.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.2.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.2.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.20.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.20.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.21.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.21.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.22.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.22.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.23.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.23.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.24.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.24.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.25.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.25.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.26.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.26.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.27.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.27.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.28.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.28.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.29.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.29.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.3.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.3.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.30.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.30.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.31.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.31.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.32.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.32.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.33.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.33.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.34.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.34.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.35.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.35.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.36.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.36.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.37.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.37.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.38.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.38.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.39.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.39.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.4.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.4.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.40.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.40.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.41.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.41.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.42.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.42.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.43.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.43.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.44.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.44.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.45.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.45.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.46.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.46.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.47.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.47.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.48.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.48.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.49.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.49.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.5.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.5.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.50.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.50.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.51.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.51.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.52.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.52.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.53.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.53.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.54.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.6.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.6.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.60.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.60.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.61.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.61.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.62.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.62.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.63.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.63.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.experts.7.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.7.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.8.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.8.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.9.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.experts.9.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.mlp.gate.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.21.self_attn.kv_a_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.kv_b_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.0.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.0.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.1.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.1.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.10.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.10.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.11.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.11.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.12.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.12.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.13.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.13.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.14.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.14.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.15.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.15.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.16.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.16.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.17.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.17.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.18.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.18.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.19.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.19.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.2.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.2.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.20.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.20.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.21.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.21.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.22.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.22.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.23.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.23.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.24.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.24.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.25.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.25.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.26.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.26.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.27.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.27.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.28.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.28.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.29.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.29.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.3.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.3.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.30.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.30.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.31.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.31.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.32.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.32.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.33.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.33.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.34.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.34.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.35.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.35.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.36.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.36.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.37.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.37.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.38.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.38.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.39.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.39.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.4.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.4.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.40.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.40.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.41.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.41.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.42.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.42.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.43.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.43.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.44.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.44.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.45.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.45.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.46.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.46.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.47.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.47.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.48.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.48.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.49.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.49.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.5.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.5.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.50.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.50.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.51.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.51.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.52.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.52.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.53.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.53.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.54.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.6.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.6.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.60.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.60.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.61.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.61.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.62.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.62.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.63.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.63.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.7.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.7.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.8.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.8.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.9.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.experts.9.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.gate.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.kv_b_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.0.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.0.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.1.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.1.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.10.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.10.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.11.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.11.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.12.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.12.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.13.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.13.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.14.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.14.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.15.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.15.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.16.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.16.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.17.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.17.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.18.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.18.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.19.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.19.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.2.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.2.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.20.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.20.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.21.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.21.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.22.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.22.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.23.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.23.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.24.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.24.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.25.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.25.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.26.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.26.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.27.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.27.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.28.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.28.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.29.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.29.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.3.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.3.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.30.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.30.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.31.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.31.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.32.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.32.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.33.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.33.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.34.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.34.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.35.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.35.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.36.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.36.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.37.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.37.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.38.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.38.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.39.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.39.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.4.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.4.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.40.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.40.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.41.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.41.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.42.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.42.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.43.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.43.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.44.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.44.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.45.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.45.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.46.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.46.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.47.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.47.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.48.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.48.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.49.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.49.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.5.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.5.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.50.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.50.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.51.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.51.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.52.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.52.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.53.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.53.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.54.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.6.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.6.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.60.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.60.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.61.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.61.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.62.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.62.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.63.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.63.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.7.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.7.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.8.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.8.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.9.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.experts.9.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.gate.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.kv_b_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.0.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.0.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.1.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.1.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.10.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.10.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.11.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.11.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.12.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.12.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.13.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.13.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.14.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.14.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.15.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.15.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.16.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.16.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.17.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.17.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.18.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.18.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.19.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.19.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.2.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.2.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.20.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.20.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.21.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.21.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.22.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.22.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.23.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.23.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.24.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.24.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.25.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.25.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.26.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.26.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.27.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.27.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.28.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.28.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.29.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.29.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.3.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.3.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.30.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.30.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.31.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.31.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.32.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.32.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.33.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.33.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.34.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.34.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.35.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.35.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.36.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.36.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.37.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.37.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.38.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.38.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.39.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.39.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.4.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.4.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.40.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.40.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.41.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.41.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.42.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.42.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.43.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.43.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.44.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.44.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.45.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.45.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.46.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.46.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.47.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.47.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.48.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.48.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.49.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.49.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.5.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.5.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.50.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.50.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.51.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.51.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.52.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.52.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.53.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.53.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.54.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.6.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.6.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.60.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.60.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.61.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.61.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.62.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.62.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.63.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.63.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.7.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.7.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.8.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.8.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.9.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.experts.9.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.gate.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.kv_b_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.0.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.0.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.1.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.1.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.10.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.10.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.11.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.11.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.12.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.12.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.13.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.13.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.14.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.14.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.15.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.15.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.16.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.16.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.17.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.17.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.18.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.18.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.19.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.19.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.2.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.2.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.20.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.20.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.21.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.21.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.22.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.22.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.23.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.23.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.24.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.24.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.25.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.25.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.26.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.26.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.27.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.27.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.28.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.28.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.29.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.29.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.3.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.3.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.30.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.30.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.31.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.31.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.32.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.32.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.33.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.33.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.34.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.34.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.35.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.35.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.36.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.36.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.37.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.37.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.38.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.38.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.39.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.39.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.4.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.4.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.40.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.40.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.41.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.41.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.42.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.42.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.43.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.43.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.44.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.44.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.45.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.45.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.46.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.46.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.47.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.47.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.48.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.48.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.49.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.49.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.5.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.5.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.50.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.50.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.51.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.51.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.52.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.52.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.53.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.53.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.54.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.54.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.55.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.55.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.56.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.56.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.57.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.57.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.58.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.58.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.59.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.59.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.6.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.6.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.60.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.60.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.61.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.61.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.62.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.62.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.63.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.63.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.7.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.7.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.8.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.8.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.9.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.experts.9.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.gate.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.kv_b_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.0.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.0.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.1.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.1.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.10.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.10.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.11.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.11.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.12.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.12.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.13.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.13.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.14.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.14.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.15.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.15.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.16.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.16.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.17.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.17.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.18.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.18.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.19.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.19.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.2.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.2.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.20.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.20.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.21.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.21.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.22.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.22.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.23.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.23.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.24.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.24.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.25.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.25.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.26.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.26.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.27.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.27.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.28.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.28.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.29.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.29.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.3.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.3.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.30.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.30.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.31.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.31.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.32.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.32.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.33.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.33.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.34.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.34.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.35.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.35.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.36.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.36.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.37.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.37.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.38.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.38.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.39.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.39.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.4.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.4.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.40.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.40.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.41.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.41.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.42.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.42.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.43.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.43.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.44.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.44.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.45.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.45.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.46.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.46.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.47.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.47.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.48.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.48.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.49.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.49.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.5.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.mlp.experts.5.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.50.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.50.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.51.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.51.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.52.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.52.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.53.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.53.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.54.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.54.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.55.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.55.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.56.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.56.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.57.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.57.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.58.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.58.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.59.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.59.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.6.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.6.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.60.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.60.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.61.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.61.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.62.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.62.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.63.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.63.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.7.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.7.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.8.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.8.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.9.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.experts.9.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.gate.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.kv_b_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.0.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.0.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.1.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.1.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.10.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.10.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.11.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.11.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.12.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.12.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.13.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.13.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.14.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.14.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.15.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.15.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.16.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.16.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.17.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.17.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.18.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.18.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.19.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.19.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.2.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.2.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.20.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.20.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.21.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.21.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.22.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.22.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.23.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.23.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.24.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.24.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.25.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.25.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.26.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.26.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.27.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.27.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.28.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.28.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.29.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.29.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.3.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.3.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.30.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.30.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.31.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.31.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.32.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.32.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.33.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.33.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.34.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.34.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.35.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.35.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.36.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.36.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.37.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.37.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.38.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.38.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.39.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.39.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.4.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.4.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.40.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.40.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.41.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.41.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.42.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.42.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.43.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.43.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.44.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.44.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.45.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.45.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.46.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.46.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.47.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.47.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.48.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.48.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.49.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.49.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.5.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.5.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.50.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.50.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.51.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.51.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.52.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.52.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.53.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.53.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.54.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.54.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.55.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.55.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.56.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.56.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.57.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.57.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.58.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.58.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.59.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.59.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.6.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.6.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.60.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.60.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.61.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.61.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.62.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.62.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.63.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.63.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.7.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.7.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.8.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.8.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.9.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.experts.9.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.gate.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.kv_b_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.0.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.0.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.1.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.1.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.10.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.10.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.11.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.11.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.12.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.12.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.13.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.13.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.14.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.14.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.15.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.15.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.16.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.16.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.17.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.17.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.18.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.18.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.19.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.19.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.2.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.2.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.20.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.20.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.21.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.21.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.22.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.22.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.23.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.23.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.24.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.24.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.25.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.25.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.26.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.26.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.27.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.27.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.28.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.28.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.29.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.29.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.3.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.3.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.30.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.30.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.31.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.31.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.32.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.32.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.33.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.33.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.34.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.34.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.35.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.35.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.36.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.36.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.37.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.37.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.38.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.38.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.39.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.39.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.4.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.4.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.40.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.40.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.41.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.41.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.42.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.42.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.43.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.43.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.44.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.44.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.45.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.45.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.46.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.46.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.47.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.47.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.48.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.48.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.49.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.49.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.5.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.5.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.50.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.50.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.51.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.51.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.52.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.52.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.53.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.53.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.54.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.54.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.55.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.55.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.56.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.56.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.57.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.57.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.58.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.58.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.59.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.59.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.6.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.6.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.60.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.60.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.61.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.61.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.62.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.62.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.63.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.63.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.experts.7.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.7.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.8.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.8.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.9.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.experts.9.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.gate.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.4.self_attn.kv_a_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.kv_b_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.0.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.0.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.1.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.1.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.10.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.10.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.11.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.11.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.12.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.12.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.13.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.13.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.14.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.14.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.15.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.15.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.16.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.16.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.17.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.17.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.18.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.18.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.19.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.19.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.2.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.2.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.20.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.20.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.21.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.21.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.22.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.22.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.23.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.23.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.24.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.24.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.25.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.25.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.26.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.26.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.27.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.27.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.28.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.28.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.29.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.29.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.3.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.3.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.30.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.30.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.31.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.31.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.32.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.32.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.33.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.33.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.34.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.34.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.35.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.35.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.36.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.36.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.37.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.37.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.38.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.38.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.39.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.39.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.4.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.4.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.40.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.40.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.41.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.41.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.42.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.42.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.43.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.43.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.44.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.44.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.45.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.45.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.46.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.46.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.47.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.47.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.48.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.48.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.49.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.49.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.5.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.5.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.50.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.50.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.51.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.51.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.52.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.52.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.53.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.53.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.54.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.54.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.55.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.55.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.56.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.56.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.57.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.57.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.58.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.58.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.59.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.59.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.6.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.6.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.60.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.60.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.61.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.61.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.62.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.62.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.63.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.63.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.7.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.7.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.8.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.8.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.9.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.experts.9.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.gate.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.kv_b_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.0.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.0.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.1.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.1.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.10.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.10.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.11.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.11.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.12.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.12.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.13.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.13.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.14.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.14.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.15.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.15.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.16.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.16.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.17.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.17.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.18.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.18.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.19.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.19.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.2.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.2.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.20.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.20.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.21.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.21.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.22.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.22.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.23.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.23.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.24.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.24.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.25.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.25.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.26.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.26.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.27.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.27.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.28.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.28.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.29.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.29.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.3.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.3.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.30.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.30.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.31.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.31.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.32.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.32.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.33.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.33.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.34.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.34.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.35.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.35.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.36.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.36.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.37.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.37.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.38.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.38.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.39.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.39.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.4.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.4.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.40.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.40.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.41.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.41.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.42.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.42.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.43.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.43.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.44.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.44.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.45.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.45.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.46.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.46.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.47.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.47.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.48.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.48.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.49.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.49.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.5.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.5.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.50.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.50.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.51.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.51.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.52.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.52.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.53.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.53.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.54.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.54.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.55.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.55.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.56.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.56.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.57.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.57.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.58.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.58.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.59.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.59.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.6.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.6.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.60.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.60.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.61.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.61.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.62.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.62.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.63.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.63.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.7.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.7.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.8.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.8.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.9.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.experts.9.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.gate.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.kv_b_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.0.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.0.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.0.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.0.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.0.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.0.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.0.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.0.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.1.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.1.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.1.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.1.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.1.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.1.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.1.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.1.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.10.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.10.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.10.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.10.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.10.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.10.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.10.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.10.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.11.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.11.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.11.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.11.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.11.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.11.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.11.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.11.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.12.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.12.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.12.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.12.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.12.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.12.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.12.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.12.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.13.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.13.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.13.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.13.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.13.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.13.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.13.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.13.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.14.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.14.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.14.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.14.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.14.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.14.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.14.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.14.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.15.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.15.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.15.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.15.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.15.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.15.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.15.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.15.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.16.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.16.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.16.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.16.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.16.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.16.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.16.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.16.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.17.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.17.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.17.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.17.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.17.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.17.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.17.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.17.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.18.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.18.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.18.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.18.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.18.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.18.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.18.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.18.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.19.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.19.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.19.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.19.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.19.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.19.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.19.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.19.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.2.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.2.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.2.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.2.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.2.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.2.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.2.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.2.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.20.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.20.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.20.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.20.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.20.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.20.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.20.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.20.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.21.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.21.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.21.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.21.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.21.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.21.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.21.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.21.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.22.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.22.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.22.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.22.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.22.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.22.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.22.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.22.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.23.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.23.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.23.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.23.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.23.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.23.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.23.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.23.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.24.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.24.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.24.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.24.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.24.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.24.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.24.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.24.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.25.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.25.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.25.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.25.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.25.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.25.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.25.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.25.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.26.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.26.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.26.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.26.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.26.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.26.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.26.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.26.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.27.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.27.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.27.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.27.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.27.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.27.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.27.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.27.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.28.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.28.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.28.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.28.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.28.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.28.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.28.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.28.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.29.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.29.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.29.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.29.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.29.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.29.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.29.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.29.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.3.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.3.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.3.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.3.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.3.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.3.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.3.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.3.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.30.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.30.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.30.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.30.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.30.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.30.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.30.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.30.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.31.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.31.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.31.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.31.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.31.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.31.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.31.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.31.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.32.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.32.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.32.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.32.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.32.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.32.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.32.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.32.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.33.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.33.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.33.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.33.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.33.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.33.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.33.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.33.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.34.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.34.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.34.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.34.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.34.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.34.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.34.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.34.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.35.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.35.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.35.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.35.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.35.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.35.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.35.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.35.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.36.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.36.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.36.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.36.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.36.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.36.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.36.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.36.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.37.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.37.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.37.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.37.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.37.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.37.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.37.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.37.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.38.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.38.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.38.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.38.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.38.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.38.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.38.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.38.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.39.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.39.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.39.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.39.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.39.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.39.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.39.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.39.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.4.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.4.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.4.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.4.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.4.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.4.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.4.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.4.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.40.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.40.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.40.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.40.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.40.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.40.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.40.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.40.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.41.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.41.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.41.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.41.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.41.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.41.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.41.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.41.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.42.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.42.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.42.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.42.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.42.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.42.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.42.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.42.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.43.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.43.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.43.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.43.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.43.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.43.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.43.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.43.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.44.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.44.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.44.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.44.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.44.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.44.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.44.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.44.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.45.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.45.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.45.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.45.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.45.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.45.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.45.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.45.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.46.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.46.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.46.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.46.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.46.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.46.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.46.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.46.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.47.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.47.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.47.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.47.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.47.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.47.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.47.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.47.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.48.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.48.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.48.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.48.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.48.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.48.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.48.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.48.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.49.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.49.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.49.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.49.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.49.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.49.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.49.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.49.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.5.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.5.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.5.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.5.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.5.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.5.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.5.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.5.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.50.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.50.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.50.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.50.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.50.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.50.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.50.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.50.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.51.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.51.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.51.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.51.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.51.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.51.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.51.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.51.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.52.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.52.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.52.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.52.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.52.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.52.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.52.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.52.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.53.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.53.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.53.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.53.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.53.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.53.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.53.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.53.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.54.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.54.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.54.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.54.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.54.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.54.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.54.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.54.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.55.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.55.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.55.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.55.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.55.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.55.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.55.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.55.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.56.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.56.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.56.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.56.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.56.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.56.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.56.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.56.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.57.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.57.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.57.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.57.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.57.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.57.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.57.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.57.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.58.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.58.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.58.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.58.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.58.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.58.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.58.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.58.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.59.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.59.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.59.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.59.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.59.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.59.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.59.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.59.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.6.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.6.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.6.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.6.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.6.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.6.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.6.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.6.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.60.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.60.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.60.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.60.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.60.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.60.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.60.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.60.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.61.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.61.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.61.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.61.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.61.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.61.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.61.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.61.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.62.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.62.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.62.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.62.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.62.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.62.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.62.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.62.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.63.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.63.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.63.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.63.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.63.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.63.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.63.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.63.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.7.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.7.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.7.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.7.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.7.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.7.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.7.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.7.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.8.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.8.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.8.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.8.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.8.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.8.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.8.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.8.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.9.base_mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.9.base_mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.9.base_mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.9.slora.learned_source.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.9.slora.lora_A.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.9.slora.lora_B.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.9.slora.rotate_layer": "model-00002-of-00007.safetensors", "model.layers.7.mlp.experts.9.slora.router.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.gate.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.kv_b_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.0.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.0.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.1.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.1.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.10.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.10.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.11.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.11.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.12.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.12.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.13.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.13.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.14.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.14.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.15.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.15.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.16.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.16.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.17.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.17.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.18.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.18.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.19.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.19.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.2.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.2.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.20.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.20.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.21.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.21.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.22.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.22.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.23.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.23.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.24.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.24.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.25.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.25.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.26.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.26.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.27.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.27.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.28.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.28.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.29.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.29.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.3.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.3.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.30.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.30.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.31.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.31.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.32.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.32.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.33.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.33.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.34.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.34.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.35.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.35.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.36.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.36.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.37.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.37.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.38.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.38.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.39.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.39.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.4.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.4.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.40.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.40.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.41.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.41.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.42.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.42.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.43.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.43.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.44.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.44.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.45.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.45.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.46.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.46.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.47.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.47.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.48.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.48.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.49.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.49.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.5.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.5.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.50.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.50.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.51.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.51.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.52.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.52.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.53.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.53.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.54.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.54.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.55.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.55.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.56.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.56.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.57.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.57.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.58.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.58.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.59.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.59.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.6.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.6.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.60.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.60.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.61.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.61.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.62.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.62.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.63.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.63.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.7.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.7.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.8.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.8.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.9.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.experts.9.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.gate.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.kv_b_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.0.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.0.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.1.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.1.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.10.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.10.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.11.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.11.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.12.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.12.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.13.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.13.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.14.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.14.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.15.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.15.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.16.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.16.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.17.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.17.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.18.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.18.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.19.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.19.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.2.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.2.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.20.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.20.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.21.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.21.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.22.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.22.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.23.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.23.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.24.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.24.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.25.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.25.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.26.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.26.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.27.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.27.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.28.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.28.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.29.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.29.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.3.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.3.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.30.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.30.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.31.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.31.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.32.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.32.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.33.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.33.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.34.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.34.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.35.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.35.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.36.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.36.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.37.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.37.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.38.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.38.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.39.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.39.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.4.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.4.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.40.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.40.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.41.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.41.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.42.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.42.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.43.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.43.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.44.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.44.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.45.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.45.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.46.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.46.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.47.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.47.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.48.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.48.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.49.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.49.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.5.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.5.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.50.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.50.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.51.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.51.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.52.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.52.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.53.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.53.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.54.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.54.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.55.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.55.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.56.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.56.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.57.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.57.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.58.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.58.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.59.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.59.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.6.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.6.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.60.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.60.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.61.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.61.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.62.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.62.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.63.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.63.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.7.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.7.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.8.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.8.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.9.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.experts.9.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.gate.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.kv_a_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.kv_a_proj_with_mqa.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.kv_b_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors" } }