ESMplusplus_6B / model.safetensors.index.json
lhallee's picture
Upload ESMplusplusForMaskedLM
0971e6e verified
Raw
History Blame Contribute Delete
67.5 kB
{
"metadata": {
"total_parameters": 6352005184,
"total_size": 25408020736
},
"weight_map": {
"embed.weight": "model-00001-of-00006.safetensors",
"sequence_head.0.bias": "model-00006-of-00006.safetensors",
"sequence_head.0.weight": "model-00006-of-00006.safetensors",
"sequence_head.2.bias": "model-00006-of-00006.safetensors",
"sequence_head.2.weight": "model-00006-of-00006.safetensors",
"sequence_head.3.bias": "model-00006-of-00006.safetensors",
"sequence_head.3.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.0.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.0.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.0.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.0.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.0.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.0.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.0.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.0.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.0.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.0.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.1.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.1.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.1.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.1.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.1.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.1.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.1.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.1.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.1.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.1.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.10.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.10.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.10.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.10.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.10.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.10.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.10.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.10.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.10.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.10.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.11.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.11.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.11.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.11.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.11.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.11.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.11.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.11.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.11.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.11.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.12.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.12.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.12.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.12.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.12.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.12.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.12.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.12.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.12.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.12.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.13.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.13.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.13.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.13.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.13.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.13.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.13.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.13.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.13.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.13.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.14.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.14.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.14.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.14.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.14.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.14.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.14.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.14.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.14.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.14.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.15.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.15.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.15.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.15.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.15.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.15.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.15.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.15.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.15.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.15.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.16.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.16.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.16.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.16.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.16.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.16.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.16.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.16.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.16.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.16.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.17.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.17.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.17.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.17.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.17.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.17.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.17.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.17.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.17.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.17.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.18.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.18.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.18.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.18.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.18.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.18.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.18.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.18.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.18.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.18.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.19.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.19.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.19.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.19.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.19.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.19.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.19.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.19.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.19.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.19.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.2.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.2.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.2.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.2.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.2.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.2.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.2.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.2.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.2.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.2.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.20.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.20.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.20.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.20.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.20.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.20.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.20.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.20.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.20.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.20.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.21.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.21.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.21.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.21.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.21.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.21.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.21.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.21.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.21.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.21.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.22.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.22.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.22.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.22.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.22.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.22.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.22.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.22.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.22.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.22.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.23.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.23.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.23.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.23.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.23.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.23.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.23.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.23.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.23.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.23.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.24.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.24.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.24.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.24.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.24.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.24.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.24.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.24.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.24.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.24.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.25.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.25.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.25.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.25.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.25.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.25.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.25.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.25.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.25.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.25.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.26.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.26.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.26.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.26.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.26.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.26.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.26.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.26.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.26.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.26.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.27.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.27.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.27.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.27.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.27.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.27.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.27.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.27.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.27.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.27.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.28.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.28.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.28.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.28.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.28.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.28.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.28.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.28.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.28.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.28.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.29.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.29.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.29.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.29.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.29.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.29.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.29.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.29.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.29.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.29.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.3.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.3.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.3.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.3.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.3.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.3.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.3.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.3.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.3.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.3.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.30.attn.k_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.30.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.30.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.30.attn.layernorm_qkv.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.30.attn.out_proj.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.30.attn.q_ln.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.30.ffn.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.30.ffn.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.30.ffn.1.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.30.ffn.3.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.31.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.31.attn.layernorm_qkv.0.bias": "model-00002-of-00006.safetensors",
"transformer.blocks.31.attn.layernorm_qkv.0.weight": "model-00002-of-00006.safetensors",
"transformer.blocks.31.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.31.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.31.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.31.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.31.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.31.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.31.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.32.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.32.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.32.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.32.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.32.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.32.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.32.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.32.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.32.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.32.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.33.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.33.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.33.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.33.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.33.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.33.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.33.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.33.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.33.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.33.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.34.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.34.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.34.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.34.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.34.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.34.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.34.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.34.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.34.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.34.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.35.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.35.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.35.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.35.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.35.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.35.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.35.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.35.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.35.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.35.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.36.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.36.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.36.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.36.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.36.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.36.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.36.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.36.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.36.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.36.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.37.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.37.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.37.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.37.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.37.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.37.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.37.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.37.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.37.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.37.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.38.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.38.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.38.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.38.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.38.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.38.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.38.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.38.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.38.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.38.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.39.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.39.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.39.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.39.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.39.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.39.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.39.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.39.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.39.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.39.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.4.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.4.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.4.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.4.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.4.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.4.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.4.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.4.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.4.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.4.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.40.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.40.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.40.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.40.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.40.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.40.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.40.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.40.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.40.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.40.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.41.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.41.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.41.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.41.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.41.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.41.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.41.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.41.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.41.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.41.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.42.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.42.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.42.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.42.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.42.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.42.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.42.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.42.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.42.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.42.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.43.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.43.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.43.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.43.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.43.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.43.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.43.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.43.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.43.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.43.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.44.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.44.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.44.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.44.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.44.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.44.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.44.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.44.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.44.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.44.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.45.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.45.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.45.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.45.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.45.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.45.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.45.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.45.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.45.ffn.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.45.ffn.3.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.46.attn.k_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.46.attn.layernorm_qkv.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.46.attn.layernorm_qkv.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.46.attn.layernorm_qkv.1.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.46.attn.out_proj.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.46.attn.q_ln.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.46.ffn.0.bias": "model-00003-of-00006.safetensors",
"transformer.blocks.46.ffn.0.weight": "model-00003-of-00006.safetensors",
"transformer.blocks.46.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.46.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.47.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.47.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.47.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.47.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.47.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.47.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.47.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.47.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.47.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.47.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.48.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.48.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.48.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.48.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.48.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.48.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.48.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.48.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.48.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.48.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.49.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.49.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.49.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.49.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.49.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.49.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.49.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.49.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.49.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.49.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.5.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.5.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.5.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.5.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.5.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.5.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.5.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.5.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.5.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.5.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.50.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.50.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.50.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.50.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.50.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.50.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.50.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.50.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.50.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.50.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.51.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.51.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.51.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.51.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.51.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.51.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.51.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.51.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.51.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.51.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.52.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.52.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.52.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.52.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.52.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.52.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.52.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.52.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.52.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.52.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.53.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.53.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.53.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.53.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.53.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.53.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.53.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.53.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.53.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.53.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.54.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.54.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.54.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.54.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.54.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.54.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.54.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.54.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.54.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.54.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.55.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.55.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.55.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.55.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.55.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.55.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.55.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.55.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.55.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.55.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.56.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.56.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.56.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.56.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.56.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.56.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.56.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.56.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.56.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.56.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.57.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.57.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.57.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.57.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.57.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.57.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.57.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.57.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.57.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.57.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.58.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.58.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.58.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.58.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.58.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.58.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.58.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.58.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.58.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.58.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.59.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.59.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.59.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.59.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.59.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.59.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.59.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.59.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.59.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.59.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.6.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.6.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.6.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.6.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.6.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.6.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.6.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.6.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.6.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.6.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.60.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.60.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.60.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.60.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.60.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.60.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.60.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.60.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.60.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.60.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.61.attn.k_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.61.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.61.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.61.attn.layernorm_qkv.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.61.attn.out_proj.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.61.attn.q_ln.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.61.ffn.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.61.ffn.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.61.ffn.1.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.61.ffn.3.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.62.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.62.attn.layernorm_qkv.0.bias": "model-00004-of-00006.safetensors",
"transformer.blocks.62.attn.layernorm_qkv.0.weight": "model-00004-of-00006.safetensors",
"transformer.blocks.62.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.62.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.62.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.62.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.62.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.62.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.62.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.63.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.63.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.63.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.63.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.63.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.63.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.63.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.63.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.63.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.63.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.64.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.64.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.64.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.64.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.64.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.64.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.64.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.64.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.64.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.64.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.65.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.65.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.65.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.65.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.65.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.65.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.65.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.65.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.65.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.65.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.66.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.66.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.66.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.66.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.66.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.66.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.66.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.66.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.66.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.66.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.67.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.67.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.67.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.67.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.67.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.67.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.67.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.67.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.67.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.67.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.68.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.68.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.68.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.68.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.68.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.68.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.68.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.68.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.68.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.68.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.69.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.69.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.69.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.69.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.69.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.69.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.69.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.69.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.69.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.69.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.7.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.7.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.7.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.7.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.7.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.7.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.7.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.7.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.7.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.7.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.70.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.70.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.70.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.70.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.70.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.70.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.70.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.70.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.70.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.70.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.71.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.71.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.71.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.71.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.71.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.71.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.71.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.71.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.71.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.71.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.72.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.72.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.72.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.72.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.72.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.72.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.72.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.72.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.72.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.72.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.73.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.73.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.73.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.73.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.73.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.73.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.73.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.73.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.73.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.73.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.74.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.74.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.74.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.74.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.74.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.74.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.74.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.74.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.74.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.74.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.75.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.75.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.75.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.75.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.75.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.75.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.75.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.75.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.75.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.75.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.76.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.76.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.76.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.76.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.76.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.76.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.76.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.76.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.76.ffn.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.76.ffn.3.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.77.attn.k_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.77.attn.layernorm_qkv.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.77.attn.layernorm_qkv.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.77.attn.layernorm_qkv.1.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.77.attn.out_proj.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.77.attn.q_ln.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.77.ffn.0.bias": "model-00005-of-00006.safetensors",
"transformer.blocks.77.ffn.0.weight": "model-00005-of-00006.safetensors",
"transformer.blocks.77.ffn.1.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.77.ffn.3.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.78.attn.k_ln.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.78.attn.layernorm_qkv.0.bias": "model-00006-of-00006.safetensors",
"transformer.blocks.78.attn.layernorm_qkv.0.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.78.attn.layernorm_qkv.1.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.78.attn.out_proj.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.78.attn.q_ln.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.78.ffn.0.bias": "model-00006-of-00006.safetensors",
"transformer.blocks.78.ffn.0.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.78.ffn.1.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.78.ffn.3.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.79.attn.k_ln.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.79.attn.layernorm_qkv.0.bias": "model-00006-of-00006.safetensors",
"transformer.blocks.79.attn.layernorm_qkv.0.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.79.attn.layernorm_qkv.1.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.79.attn.out_proj.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.79.attn.q_ln.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.79.ffn.0.bias": "model-00006-of-00006.safetensors",
"transformer.blocks.79.ffn.0.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.79.ffn.1.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.79.ffn.3.weight": "model-00006-of-00006.safetensors",
"transformer.blocks.8.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.8.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.8.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.8.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.8.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.8.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.8.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.8.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.8.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.8.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.9.attn.k_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.9.attn.layernorm_qkv.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.9.attn.layernorm_qkv.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.9.attn.layernorm_qkv.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.9.attn.out_proj.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.9.attn.q_ln.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.9.ffn.0.bias": "model-00001-of-00006.safetensors",
"transformer.blocks.9.ffn.0.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.9.ffn.1.weight": "model-00001-of-00006.safetensors",
"transformer.blocks.9.ffn.3.weight": "model-00001-of-00006.safetensors",
"transformer.norm.weight": "model-00006-of-00006.safetensors"
}
}