model.safetensors.index.json

{
  "metadata": {
    "total_size": 398180
  },
  "weight_map": {
    "embed_out.weight": "model-00004-of-00004.safetensors",
    "gpt_neox.embed_in.weight": "model-00001-of-00004.safetensors",
    "gpt_neox.final_layer_norm.bias": "model-00003-of-00004.safetensors",
    "gpt_neox.final_layer_norm.weight": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.0.attention.dense.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.0.attention.dense.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.0.input_layernorm.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.attention.dense.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.attention.dense.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.input_layernorm.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.attention.dense.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.attention.dense.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.input_layernorm.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.3.attention.dense.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.3.attention.dense.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.3.input_layernorm.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
    "gpt_neox.layers.4.attention.dense.bias": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.4.attention.dense.weight": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.4.input_layernorm.bias": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00003-of-00004.safetensors",
    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors"
  }
}