pytorch_model.bin.index.json

{
  "metadata": {
    "total_size": 1264918528
  },
  "weight_map": {
    "lm_head.weight": "pytorch_model-00001-of-00002.bin",
    "model.final_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.final_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.0.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.14.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.15.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.15.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.15.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.15.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.16.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.16.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.16.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.16.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.17.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.17.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.17.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.17.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.18.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.18.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.18.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.18.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.19.attn.c_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.19.attn.qkv_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.19.mlp.c_fc.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.19.mlp.c_proj.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "model.layers.2.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.attn.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.attn.qkv_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.mlp.c_fc.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.mlp.c_proj.weight": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "model.word_embeddings.weight": "pytorch_model-00001-of-00002.bin"
  }
}