CDS-starcoder2-16b-20241031_pretrain / model.safetensors.index.json
AndreyRzhaksinskiy's picture
Upload Starcoder2ForCausalLM
a015e21 verified
raw
history blame
52.1 kB
{
"metadata": {
"total_size": 31915778048
},
"weight_map": {
"lm_head.weight": "model-00007-of-00007.safetensors",
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
"model.layers.0.input_layernorm.bias": "model-00001-of-00007.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.o_proj.bias": "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.bias": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.input_layernorm.bias": "model-00001-of-00007.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.o_proj.bias": "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.bias": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.10.input_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.10.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
"model.layers.10.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
"model.layers.10.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.10.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.10.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.input_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.11.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
"model.layers.11.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
"model.layers.11.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.11.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.12.input_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.12.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
"model.layers.12.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
"model.layers.12.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.12.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.12.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.o_proj.bias": "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.bias": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.13.input_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.13.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
"model.layers.13.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
"model.layers.13.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.13.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.13.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.13.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.13.self_attn.o_proj.bias": "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.bias": "model-00003-of-00007.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.13.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.14.input_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.14.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.14.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
"model.layers.14.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
"model.layers.14.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.14.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.14.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.14.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.14.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.14.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.14.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.15.input_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.15.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
"model.layers.15.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
"model.layers.15.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.15.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.15.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.15.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.15.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.15.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.15.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.16.input_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.16.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
"model.layers.16.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
"model.layers.16.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.16.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.16.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.16.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.17.input_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.17.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
"model.layers.17.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
"model.layers.17.mlp.c_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.17.mlp.c_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.17.post_attention_layernorm.bias": "model-00003-of-00007.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.17.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.18.input_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.18.mlp.c_fc.bias": "model-00003-of-00007.safetensors",
"model.layers.18.mlp.c_fc.weight": "model-00003-of-00007.safetensors",
"model.layers.18.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.18.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.18.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.18.self_attn.o_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.19.input_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.19.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.19.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
"model.layers.19.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
"model.layers.19.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.19.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.19.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.19.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.19.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.19.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.19.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.2.input_layernorm.bias": "model-00001-of-00007.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.2.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
"model.layers.2.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
"model.layers.2.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.2.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.o_proj.bias": "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.bias": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.20.input_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.20.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.20.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
"model.layers.20.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
"model.layers.20.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.20.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.20.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.20.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.20.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.20.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.20.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.21.input_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.21.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.21.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
"model.layers.21.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
"model.layers.21.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.21.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.21.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.21.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.21.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.21.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.21.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.22.input_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.22.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.22.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
"model.layers.22.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
"model.layers.22.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.22.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.22.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.22.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.22.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.22.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.22.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.23.input_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.23.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.23.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
"model.layers.23.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
"model.layers.23.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.23.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.23.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.23.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.23.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.23.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.23.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.24.input_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.24.mlp.c_fc.bias": "model-00004-of-00007.safetensors",
"model.layers.24.mlp.c_fc.weight": "model-00004-of-00007.safetensors",
"model.layers.24.mlp.c_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.24.mlp.c_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.24.post_attention_layernorm.bias": "model-00004-of-00007.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.24.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.24.self_attn.o_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.24.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.24.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.25.input_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.25.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.25.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
"model.layers.25.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
"model.layers.25.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.25.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.25.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.25.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.26.input_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.26.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.26.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
"model.layers.26.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
"model.layers.26.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.26.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.26.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.26.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.26.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.26.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.26.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.27.input_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.27.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.27.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
"model.layers.27.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
"model.layers.27.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.27.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.27.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.27.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.27.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.27.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.27.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.28.input_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.28.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.28.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
"model.layers.28.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
"model.layers.28.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.28.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.28.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.28.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.28.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.28.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.28.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.29.input_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.29.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.29.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
"model.layers.29.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
"model.layers.29.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.29.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.29.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.29.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.29.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.29.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.29.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.3.input_layernorm.bias": "model-00001-of-00007.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.3.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
"model.layers.3.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
"model.layers.3.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.3.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.o_proj.bias": "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.bias": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.30.input_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.30.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.30.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
"model.layers.30.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
"model.layers.30.mlp.c_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.30.mlp.c_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.30.post_attention_layernorm.bias": "model-00005-of-00007.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.30.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.30.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.30.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.30.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.31.input_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.31.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.31.mlp.c_fc.bias": "model-00005-of-00007.safetensors",
"model.layers.31.mlp.c_fc.weight": "model-00005-of-00007.safetensors",
"model.layers.31.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.31.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.31.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.31.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.31.self_attn.o_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.31.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.31.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.32.input_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.32.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.32.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
"model.layers.32.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
"model.layers.32.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.32.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.32.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.32.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.32.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.32.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.32.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.33.input_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.33.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.33.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
"model.layers.33.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
"model.layers.33.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.33.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.33.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.33.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.33.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.33.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.33.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.34.input_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.34.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.34.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
"model.layers.34.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
"model.layers.34.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.34.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.34.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.34.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.34.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.34.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.34.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.35.input_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.35.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.35.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
"model.layers.35.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
"model.layers.35.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.35.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.35.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.35.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.35.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.35.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.35.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.36.input_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.36.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.36.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
"model.layers.36.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
"model.layers.36.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.36.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.36.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.36.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.36.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.36.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.36.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.37.input_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.37.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.37.mlp.c_fc.bias": "model-00006-of-00007.safetensors",
"model.layers.37.mlp.c_fc.weight": "model-00006-of-00007.safetensors",
"model.layers.37.mlp.c_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.37.mlp.c_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.37.post_attention_layernorm.bias": "model-00006-of-00007.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.37.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.37.self_attn.o_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.37.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.37.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.38.input_layernorm.bias": "model-00007-of-00007.safetensors",
"model.layers.38.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.38.mlp.c_fc.bias": "model-00007-of-00007.safetensors",
"model.layers.38.mlp.c_fc.weight": "model-00007-of-00007.safetensors",
"model.layers.38.mlp.c_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.38.mlp.c_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.38.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.38.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.38.self_attn.o_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.38.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.38.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.39.input_layernorm.bias": "model-00007-of-00007.safetensors",
"model.layers.39.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.39.mlp.c_fc.bias": "model-00007-of-00007.safetensors",
"model.layers.39.mlp.c_fc.weight": "model-00007-of-00007.safetensors",
"model.layers.39.mlp.c_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.39.mlp.c_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.39.post_attention_layernorm.bias": "model-00007-of-00007.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.39.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.39.self_attn.o_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.39.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.39.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.4.input_layernorm.bias": "model-00001-of-00007.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.4.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
"model.layers.4.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
"model.layers.4.mlp.c_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.4.mlp.c_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.4.post_attention_layernorm.bias": "model-00001-of-00007.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.o_proj.bias": "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.bias": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.5.input_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.5.mlp.c_fc.bias": "model-00001-of-00007.safetensors",
"model.layers.5.mlp.c_fc.weight": "model-00001-of-00007.safetensors",
"model.layers.5.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.5.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.5.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.o_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.6.input_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.6.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
"model.layers.6.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
"model.layers.6.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.6.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.o_proj.bias": "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.bias": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.input_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.7.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
"model.layers.7.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
"model.layers.7.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.7.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.o_proj.bias": "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.bias": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.input_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.8.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
"model.layers.8.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
"model.layers.8.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.8.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.o_proj.bias": "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.bias": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.input_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.9.mlp.c_fc.bias": "model-00002-of-00007.safetensors",
"model.layers.9.mlp.c_fc.weight": "model-00002-of-00007.safetensors",
"model.layers.9.mlp.c_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.9.mlp.c_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.post_attention_layernorm.bias": "model-00002-of-00007.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.o_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.norm.bias": "model-00007-of-00007.safetensors",
"model.norm.weight": "model-00007-of-00007.safetensors"
}
}