| { | |
| "metadata": { | |
| "total_size": 8346803072 | |
| }, | |
| "weight_map": { | |
| "lm_head.weight": "model-00002-of-00002.safetensors", | |
| "model.embed_tokens.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.0.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.0.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.0.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.0.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.router.norm1.num_batches_tracked": "model-00001-of-00002.safetensors", | |
| "model.layers.0.router.norm1.running_mean": "model-00001-of-00002.safetensors", | |
| "model.layers.0.router.norm1.running_var": "model-00001-of-00002.safetensors", | |
| "model.layers.0.router.norm2.num_batches_tracked": "model-00001-of-00002.safetensors", | |
| "model.layers.0.router.norm2.running_mean": "model-00001-of-00002.safetensors", | |
| "model.layers.0.router.norm2.running_var": "model-00001-of-00002.safetensors", | |
| "model.layers.0.router.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.router.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.1.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.1.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.1.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.1.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.10.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.10.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.10.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.10.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.11.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.11.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.11.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.11.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.12.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.12.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.12.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.12.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.router.norm1.num_batches_tracked": "model-00001-of-00002.safetensors", | |
| "model.layers.12.router.norm1.running_mean": "model-00001-of-00002.safetensors", | |
| "model.layers.12.router.norm1.running_var": "model-00001-of-00002.safetensors", | |
| "model.layers.12.router.norm2.num_batches_tracked": "model-00001-of-00002.safetensors", | |
| "model.layers.12.router.norm2.running_mean": "model-00001-of-00002.safetensors", | |
| "model.layers.12.router.norm2.running_var": "model-00001-of-00002.safetensors", | |
| "model.layers.12.router.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.router.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.13.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.13.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.13.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.13.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.14.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.14.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.14.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.14.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.15.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.15.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.15.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.15.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.16.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.16.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.16.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.16.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.router.norm1.num_batches_tracked": "model-00001-of-00002.safetensors", | |
| "model.layers.16.router.norm1.running_mean": "model-00001-of-00002.safetensors", | |
| "model.layers.16.router.norm1.running_var": "model-00001-of-00002.safetensors", | |
| "model.layers.16.router.norm2.num_batches_tracked": "model-00001-of-00002.safetensors", | |
| "model.layers.16.router.norm2.running_mean": "model-00001-of-00002.safetensors", | |
| "model.layers.16.router.norm2.running_var": "model-00001-of-00002.safetensors", | |
| "model.layers.16.router.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.router.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.17.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.17.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.17.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.17.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.18.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.18.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.18.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.18.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.19.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.19.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.19.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.19.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.2.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.2.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.2.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.2.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.20.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.20.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.20.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.20.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.router.norm1.num_batches_tracked": "model-00002-of-00002.safetensors", | |
| "model.layers.20.router.norm1.running_mean": "model-00002-of-00002.safetensors", | |
| "model.layers.20.router.norm1.running_var": "model-00002-of-00002.safetensors", | |
| "model.layers.20.router.norm2.num_batches_tracked": "model-00002-of-00002.safetensors", | |
| "model.layers.20.router.norm2.running_mean": "model-00002-of-00002.safetensors", | |
| "model.layers.20.router.norm2.running_var": "model-00002-of-00002.safetensors", | |
| "model.layers.20.router.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.router.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.21.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.21.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.21.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.21.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.22.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.22.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.22.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.22.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.23.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.23.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.23.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.23.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.24.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.24.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.24.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.24.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.router.norm1.num_batches_tracked": "model-00002-of-00002.safetensors", | |
| "model.layers.24.router.norm1.running_mean": "model-00002-of-00002.safetensors", | |
| "model.layers.24.router.norm1.running_var": "model-00002-of-00002.safetensors", | |
| "model.layers.24.router.norm2.num_batches_tracked": "model-00002-of-00002.safetensors", | |
| "model.layers.24.router.norm2.running_mean": "model-00002-of-00002.safetensors", | |
| "model.layers.24.router.norm2.running_var": "model-00002-of-00002.safetensors", | |
| "model.layers.24.router.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.router.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.25.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.25.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.25.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.25.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.26.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.26.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.26.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.26.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.27.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.27.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.27.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.27.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.28.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.28.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.28.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.28.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.router.norm1.num_batches_tracked": "model-00002-of-00002.safetensors", | |
| "model.layers.28.router.norm1.running_mean": "model-00002-of-00002.safetensors", | |
| "model.layers.28.router.norm1.running_var": "model-00002-of-00002.safetensors", | |
| "model.layers.28.router.norm2.num_batches_tracked": "model-00002-of-00002.safetensors", | |
| "model.layers.28.router.norm2.running_mean": "model-00002-of-00002.safetensors", | |
| "model.layers.28.router.norm2.running_var": "model-00002-of-00002.safetensors", | |
| "model.layers.28.router.w1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.router.w2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.29.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.29.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.29.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.29.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.3.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.3.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.3.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.3.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.30.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.30.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.30.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.30.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.moe.b1": "model-00002-of-00002.safetensors", | |
| "model.layers.31.moe.b2": "model-00002-of-00002.safetensors", | |
| "model.layers.31.moe.u1.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.31.moe.u1.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.moe.u2.bias": "model-00002-of-00002.safetensors", | |
| "model.layers.31.moe.u2.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.moe.v11.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.moe.v12.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.moe.v21.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.moe.v22.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", | |
| "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.4.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.4.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.4.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.4.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.router.norm1.num_batches_tracked": "model-00001-of-00002.safetensors", | |
| "model.layers.4.router.norm1.running_mean": "model-00001-of-00002.safetensors", | |
| "model.layers.4.router.norm1.running_var": "model-00001-of-00002.safetensors", | |
| "model.layers.4.router.norm2.num_batches_tracked": "model-00001-of-00002.safetensors", | |
| "model.layers.4.router.norm2.running_mean": "model-00001-of-00002.safetensors", | |
| "model.layers.4.router.norm2.running_var": "model-00001-of-00002.safetensors", | |
| "model.layers.4.router.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.router.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.5.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.5.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.5.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.5.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.6.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.6.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.6.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.6.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.7.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.7.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.7.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.7.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.8.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.8.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.8.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.8.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.router.norm1.num_batches_tracked": "model-00001-of-00002.safetensors", | |
| "model.layers.8.router.norm1.running_mean": "model-00001-of-00002.safetensors", | |
| "model.layers.8.router.norm1.running_var": "model-00001-of-00002.safetensors", | |
| "model.layers.8.router.norm2.num_batches_tracked": "model-00001-of-00002.safetensors", | |
| "model.layers.8.router.norm2.running_mean": "model-00001-of-00002.safetensors", | |
| "model.layers.8.router.norm2.running_var": "model-00001-of-00002.safetensors", | |
| "model.layers.8.router.w1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.router.w2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.moe.b1": "model-00001-of-00002.safetensors", | |
| "model.layers.9.moe.b2": "model-00001-of-00002.safetensors", | |
| "model.layers.9.moe.u1.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.9.moe.u1.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.moe.u2.bias": "model-00001-of-00002.safetensors", | |
| "model.layers.9.moe.u2.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.moe.v11.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.moe.v12.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.moe.v21.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.moe.v22.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", | |
| "model.norm.weight": "model-00002-of-00002.safetensors" | |
| } | |
| } | |