| {"metadata": {"format": "pt"}, "weight_map": {"gpt_neox.embed_in.weight": "pytorch_model-00000.bin", "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00000.bin", "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00000.bin", "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00000.bin", "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00000.bin", "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00000.bin", "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00000.bin", "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00000.bin", "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00000.bin", "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00000.bin", "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00000.bin", "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00000.bin", "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00000.bin", "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00000.bin", "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00000.bin", "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00000.bin", "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00000.bin", "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00000.bin", "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00000.bin", "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00000.bin", "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00000.bin", "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00000.bin", "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00000.bin", "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00000.bin", "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00000.bin", "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00000.bin", "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00000.bin", "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00000.bin", "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00000.bin", "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00000.bin", "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00000.bin", "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00000.bin", "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00000.bin", "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00000.bin", "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00000.bin", "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00000.bin", "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00000.bin", "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00000.bin", "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00000.bin", "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00000.bin", "gpt_neox.final_layer_norm.weight": "pytorch_model-00000.bin", "gpt_neox.final_layer_norm.bias": "pytorch_model-00000.bin", "score.weight": "pytorch_model-00000.bin"}} |