{ "metadata": { "total_size": 130585766048.0 }, "weight_map": { "embed_out.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.final_layer_norm.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.final_layer_norm.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.10.attention.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.attention.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.12.attention.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.attention.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.attention.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.attention.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.attention.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.attention.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin", "gpt_neox.layers.18.attention.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.attention.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.20.attention.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.attention.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.attention.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.attention.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin", "gpt_neox.layers.24.attention.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.attention.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.attention.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.attention.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.attention.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.attention.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin", "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.30.attention.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.attention.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.attention.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.attention.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.attention.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.attention.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin", "gpt_neox.layers.36.attention.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.attention.dense.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.attention.dense.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.attention.masked_bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.attention.query_key_value.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.attention.query_key_value.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.input_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.post_attention_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.attention.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.attention.dense.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.attention.dense.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.attention.masked_bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.attention.query_key_value.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.attention.query_key_value.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.input_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.post_attention_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.attention.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.attention.dense.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.attention.dense.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.attention.masked_bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.attention.query_key_value.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.attention.query_key_value.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.input_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.post_attention_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.attention.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.attention.dense.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.attention.dense.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.attention.masked_bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.attention.query_key_value.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.attention.query_key_value.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.input_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.post_attention_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.40.attention.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.attention.dense.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.attention.dense.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.attention.masked_bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.attention.query_key_value.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.attention.query_key_value.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.input_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.input_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.post_attention_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.40.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.attention.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.attention.dense.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.attention.dense.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.attention.masked_bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.attention.query_key_value.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.attention.query_key_value.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.input_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.41.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.41.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.post_attention_layernorm.bias": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.41.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin", "gpt_neox.layers.42.attention.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.attention.dense.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.attention.dense.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.attention.masked_bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.attention.query_key_value.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.attention.query_key_value.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.input_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.post_attention_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.attention.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.attention.dense.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.attention.dense.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.attention.masked_bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.attention.query_key_value.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.attention.query_key_value.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.input_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.post_attention_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.attention.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.attention.dense.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.attention.dense.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.attention.masked_bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.attention.query_key_value.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.attention.query_key_value.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.input_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.post_attention_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.attention.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.attention.dense.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.attention.dense.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.attention.masked_bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.attention.query_key_value.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.attention.query_key_value.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.input_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.input_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.post_attention_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.45.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.attention.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.attention.dense.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.attention.dense.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.attention.masked_bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.attention.query_key_value.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.attention.query_key_value.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.input_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.input_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.post_attention_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.46.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.attention.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.attention.dense.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.attention.dense.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.attention.masked_bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.attention.query_key_value.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.attention.query_key_value.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.input_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.input_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.47.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.47.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.post_attention_layernorm.bias": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.47.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin", "gpt_neox.layers.48.attention.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.attention.dense.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.attention.dense.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.attention.masked_bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.attention.query_key_value.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.attention.query_key_value.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.attention.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.input_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.post_attention_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.48.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.attention.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.attention.dense.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.attention.dense.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.attention.masked_bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.attention.query_key_value.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.attention.query_key_value.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.attention.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.input_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.post_attention_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.49.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin", "gpt_neox.layers.50.attention.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.attention.dense.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.attention.dense.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.attention.masked_bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.attention.query_key_value.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.attention.query_key_value.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.attention.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.input_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.post_attention_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.attention.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.attention.dense.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.attention.dense.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.attention.masked_bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.attention.query_key_value.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.attention.query_key_value.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.attention.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.input_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.input_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.post_attention_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.51.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.attention.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.attention.dense.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.attention.dense.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.attention.masked_bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.attention.query_key_value.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.attention.query_key_value.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.attention.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.input_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.input_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.post_attention_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.52.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.attention.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.attention.dense.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.attention.dense.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.attention.masked_bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.attention.query_key_value.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.attention.query_key_value.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.attention.rotary_emb.inv_freq": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.input_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.input_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.53.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.53.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.post_attention_layernorm.bias": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.53.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin", "gpt_neox.layers.54.attention.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.attention.dense.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.attention.dense.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.attention.masked_bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.attention.query_key_value.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.attention.query_key_value.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.attention.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.input_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.post_attention_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.54.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.attention.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.attention.dense.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.attention.dense.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.attention.masked_bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.attention.query_key_value.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.attention.query_key_value.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.attention.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.input_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.post_attention_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.55.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.attention.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.attention.dense.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.attention.dense.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.attention.masked_bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.attention.query_key_value.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.attention.query_key_value.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.attention.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.input_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.post_attention_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.56.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.attention.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.attention.dense.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.attention.dense.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.attention.masked_bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.attention.query_key_value.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.attention.query_key_value.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.attention.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.input_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.input_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.post_attention_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.57.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.attention.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.attention.dense.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.attention.dense.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.attention.masked_bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.attention.query_key_value.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.attention.query_key_value.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.attention.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.input_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.input_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.mlp.dense_4h_to_h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.post_attention_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.58.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.attention.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.attention.dense.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.attention.dense.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.attention.masked_bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.attention.query_key_value.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.attention.query_key_value.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.attention.rotary_emb.inv_freq": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.input_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.input_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.59.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.59.mlp.dense_h_to_4h.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.post_attention_layernorm.bias": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.59.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin", "gpt_neox.layers.6.attention.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.60.attention.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.attention.dense.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.attention.dense.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.attention.masked_bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.attention.query_key_value.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.attention.query_key_value.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.attention.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.input_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.post_attention_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.60.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.attention.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.attention.dense.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.attention.dense.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.attention.masked_bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.attention.query_key_value.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.attention.query_key_value.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.attention.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.input_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.post_attention_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.61.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.attention.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.attention.dense.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.attention.dense.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.attention.masked_bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.attention.query_key_value.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.attention.query_key_value.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.attention.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.input_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.post_attention_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.62.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.attention.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.attention.dense.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.attention.dense.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.attention.masked_bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.attention.query_key_value.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.attention.query_key_value.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.attention.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.input_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.input_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.post_attention_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.63.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.attention.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.attention.dense.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.attention.dense.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.attention.masked_bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.attention.query_key_value.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.attention.query_key_value.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.attention.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.input_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.input_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.mlp.dense_4h_to_h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.post_attention_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.64.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.attention.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.attention.dense.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.attention.dense.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.attention.masked_bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.attention.query_key_value.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.attention.query_key_value.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.attention.rotary_emb.inv_freq": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.input_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.input_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.65.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.65.mlp.dense_h_to_4h.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.post_attention_layernorm.bias": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.65.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin", "gpt_neox.layers.66.attention.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.attention.dense.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.attention.dense.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.attention.masked_bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.attention.query_key_value.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.attention.query_key_value.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.attention.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.input_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.post_attention_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.66.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.attention.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.attention.dense.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.attention.dense.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.attention.masked_bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.attention.query_key_value.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.attention.query_key_value.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.attention.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.input_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.post_attention_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.67.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.attention.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.attention.dense.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.attention.dense.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.attention.masked_bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.attention.query_key_value.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.attention.query_key_value.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.attention.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.input_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.input_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.post_attention_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.68.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.attention.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.attention.dense.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.attention.dense.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.attention.masked_bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.attention.query_key_value.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.attention.query_key_value.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.attention.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.input_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.input_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.post_attention_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.69.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.7.attention.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.70.attention.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.attention.dense.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.attention.dense.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.attention.masked_bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.attention.query_key_value.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.attention.query_key_value.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.attention.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.input_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.input_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.mlp.dense_4h_to_h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.post_attention_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.70.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.attention.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.attention.dense.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.attention.dense.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.attention.masked_bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.attention.query_key_value.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.attention.query_key_value.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.attention.rotary_emb.inv_freq": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.input_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.input_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.71.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.71.mlp.dense_h_to_4h.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.post_attention_layernorm.bias": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.71.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin", "gpt_neox.layers.72.attention.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.attention.dense.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.attention.dense.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.attention.masked_bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.attention.query_key_value.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.attention.query_key_value.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.attention.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.input_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.post_attention_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.72.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.attention.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.attention.dense.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.attention.dense.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.attention.masked_bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.attention.query_key_value.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.attention.query_key_value.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.attention.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.input_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.post_attention_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.73.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.attention.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.attention.dense.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.attention.dense.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.attention.masked_bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.attention.query_key_value.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.attention.query_key_value.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.attention.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.input_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.input_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.post_attention_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.74.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.attention.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.attention.dense.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.attention.dense.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.attention.masked_bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.attention.query_key_value.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.attention.query_key_value.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.attention.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.input_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.input_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.post_attention_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.75.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.attention.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.attention.dense.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.attention.dense.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.attention.masked_bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.attention.query_key_value.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.attention.query_key_value.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.attention.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.input_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.input_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.mlp.dense_4h_to_h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.post_attention_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.76.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.attention.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.attention.dense.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.attention.dense.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.attention.masked_bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.attention.query_key_value.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.attention.query_key_value.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.attention.rotary_emb.inv_freq": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.input_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.input_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.77.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.77.mlp.dense_h_to_4h.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.post_attention_layernorm.bias": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.77.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin", "gpt_neox.layers.78.attention.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.attention.dense.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.attention.dense.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.attention.masked_bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.attention.query_key_value.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.attention.query_key_value.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.attention.rotary_emb.inv_freq": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.input_layernorm.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.mlp.dense_h_to_4h.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.post_attention_layernorm.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.78.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.attention.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.attention.dense.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.attention.dense.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.attention.masked_bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.attention.query_key_value.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.attention.query_key_value.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.attention.rotary_emb.inv_freq": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.input_layernorm.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.mlp.dense_4h_to_h.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.mlp.dense_h_to_4h.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.post_attention_layernorm.bias": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.79.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin", "gpt_neox.layers.8.attention.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.attention.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00014.bin", "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin" } }