gpt-neox-20b / flax_model.msgpack.index.json
heegyu's picture
Upload FlaxGPTNeoXForCausalLM
f0c78df
{
"metadata": {
"total_size": 41109135360
},
"weight_map": {
"embed_out/kernel": "flax_model-00005-of-00005.msgpack",
"gpt_neox/embed_in/embedding": "flax_model-00001-of-00005.msgpack",
"gpt_neox/final_layer_norm/bias": "flax_model-00005-of-00005.msgpack",
"gpt_neox/final_layer_norm/scale": "flax_model-00005-of-00005.msgpack",
"gpt_neox/layers/0/attention/dense/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/0/attention/dense/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/0/attention/query_key_value/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/0/attention/query_key_value/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/0/input_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/0/input_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/0/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/0/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/0/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/0/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/0/post_attention_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/0/post_attention_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/attention/dense/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/attention/dense/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/attention/query_key_value/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/attention/query_key_value/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/input_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/input_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/post_attention_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/1/post_attention_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/10/attention/dense/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/10/attention/dense/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/10/attention/query_key_value/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/10/attention/query_key_value/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/10/input_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/10/input_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/10/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/10/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/10/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/10/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/10/post_attention_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/10/post_attention_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/11/attention/dense/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/11/attention/dense/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/11/attention/query_key_value/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/11/attention/query_key_value/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/11/input_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/11/input_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/11/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/11/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/11/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/11/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/11/post_attention_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/11/post_attention_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/attention/dense/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/attention/dense/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/attention/query_key_value/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/attention/query_key_value/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/input_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/input_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/post_attention_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/12/post_attention_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/attention/dense/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/attention/dense/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/attention/query_key_value/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/attention/query_key_value/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/input_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/input_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/post_attention_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/13/post_attention_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/attention/dense/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/attention/dense/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/attention/query_key_value/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/attention/query_key_value/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/input_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/input_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/post_attention_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/14/post_attention_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/attention/dense/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/attention/dense/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/attention/query_key_value/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/attention/query_key_value/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/input_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/input_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/post_attention_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/15/post_attention_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/attention/dense/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/attention/dense/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/attention/query_key_value/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/attention/query_key_value/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/input_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/input_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/post_attention_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/16/post_attention_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/attention/dense/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/attention/dense/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/attention/query_key_value/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/attention/query_key_value/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/input_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/input_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/post_attention_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/17/post_attention_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/attention/dense/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/attention/dense/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/attention/query_key_value/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/attention/query_key_value/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/input_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/input_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/post_attention_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/18/post_attention_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/attention/dense/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/attention/dense/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/attention/query_key_value/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/attention/query_key_value/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/input_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/input_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/post_attention_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/19/post_attention_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/2/attention/dense/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/2/attention/dense/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/2/attention/query_key_value/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/2/attention/query_key_value/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/2/input_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/2/input_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/2/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/2/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/2/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/2/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/2/post_attention_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/2/post_attention_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/20/attention/dense/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/20/attention/dense/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/20/attention/query_key_value/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/20/attention/query_key_value/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/20/input_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/20/input_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/20/mlp/dense_4h_to_h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/20/mlp/dense_4h_to_h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/20/mlp/dense_h_to_4h/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/20/mlp/dense_h_to_4h/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/20/post_attention_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/20/post_attention_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/21/attention/dense/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/21/attention/dense/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/21/attention/query_key_value/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/21/attention/query_key_value/kernel": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/21/input_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/21/input_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/21/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/21/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/21/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/21/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/21/post_attention_layernorm/bias": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/21/post_attention_layernorm/scale": "flax_model-00002-of-00005.msgpack",
"gpt_neox/layers/22/attention/dense/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/22/attention/dense/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/22/attention/query_key_value/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/22/attention/query_key_value/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/22/input_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/22/input_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/22/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/22/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/22/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/22/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/22/post_attention_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/22/post_attention_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/attention/dense/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/attention/dense/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/attention/query_key_value/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/attention/query_key_value/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/input_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/input_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/post_attention_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/23/post_attention_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/attention/dense/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/attention/dense/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/attention/query_key_value/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/attention/query_key_value/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/input_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/input_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/post_attention_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/24/post_attention_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/attention/dense/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/attention/dense/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/attention/query_key_value/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/attention/query_key_value/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/input_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/input_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/post_attention_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/25/post_attention_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/attention/dense/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/attention/dense/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/attention/query_key_value/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/attention/query_key_value/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/input_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/input_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/post_attention_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/26/post_attention_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/attention/dense/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/attention/dense/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/attention/query_key_value/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/attention/query_key_value/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/input_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/input_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/post_attention_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/27/post_attention_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/attention/dense/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/attention/dense/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/attention/query_key_value/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/attention/query_key_value/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/input_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/input_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/post_attention_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/28/post_attention_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/attention/dense/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/attention/dense/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/attention/query_key_value/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/attention/query_key_value/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/input_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/input_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/post_attention_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/29/post_attention_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/3/attention/dense/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/3/attention/dense/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/3/attention/query_key_value/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/3/attention/query_key_value/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/3/input_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/3/input_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/3/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/3/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/3/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/3/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/3/post_attention_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/3/post_attention_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/30/attention/dense/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/30/attention/dense/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/30/attention/query_key_value/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/30/attention/query_key_value/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/30/input_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/30/input_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/30/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/30/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/30/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/30/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/30/post_attention_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/30/post_attention_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/attention/dense/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/attention/dense/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/attention/query_key_value/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/attention/query_key_value/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/input_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/input_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/mlp/dense_4h_to_h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/mlp/dense_4h_to_h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/mlp/dense_h_to_4h/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/mlp/dense_h_to_4h/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/post_attention_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/31/post_attention_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/32/attention/dense/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/32/attention/dense/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/32/attention/query_key_value/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/32/attention/query_key_value/kernel": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/32/input_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/32/input_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/32/mlp/dense_4h_to_h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/32/mlp/dense_4h_to_h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/32/mlp/dense_h_to_4h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/32/mlp/dense_h_to_4h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/32/post_attention_layernorm/bias": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/32/post_attention_layernorm/scale": "flax_model-00003-of-00005.msgpack",
"gpt_neox/layers/33/attention/dense/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/33/attention/dense/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/33/attention/query_key_value/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/33/attention/query_key_value/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/33/input_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/33/input_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/33/mlp/dense_4h_to_h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/33/mlp/dense_4h_to_h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/33/mlp/dense_h_to_4h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/33/mlp/dense_h_to_4h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/33/post_attention_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/33/post_attention_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/attention/dense/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/attention/dense/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/attention/query_key_value/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/attention/query_key_value/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/input_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/input_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/mlp/dense_4h_to_h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/mlp/dense_4h_to_h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/mlp/dense_h_to_4h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/mlp/dense_h_to_4h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/post_attention_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/34/post_attention_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/attention/dense/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/attention/dense/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/attention/query_key_value/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/attention/query_key_value/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/input_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/input_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/mlp/dense_4h_to_h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/mlp/dense_4h_to_h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/mlp/dense_h_to_4h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/mlp/dense_h_to_4h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/post_attention_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/35/post_attention_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/attention/dense/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/attention/dense/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/attention/query_key_value/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/attention/query_key_value/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/input_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/input_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/mlp/dense_4h_to_h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/mlp/dense_4h_to_h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/mlp/dense_h_to_4h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/mlp/dense_h_to_4h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/post_attention_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/36/post_attention_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/attention/dense/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/attention/dense/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/attention/query_key_value/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/attention/query_key_value/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/input_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/input_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/mlp/dense_4h_to_h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/mlp/dense_4h_to_h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/mlp/dense_h_to_4h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/mlp/dense_h_to_4h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/post_attention_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/37/post_attention_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/attention/dense/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/attention/dense/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/attention/query_key_value/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/attention/query_key_value/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/input_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/input_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/mlp/dense_4h_to_h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/mlp/dense_4h_to_h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/mlp/dense_h_to_4h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/mlp/dense_h_to_4h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/post_attention_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/38/post_attention_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/attention/dense/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/attention/dense/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/attention/query_key_value/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/attention/query_key_value/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/input_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/input_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/mlp/dense_4h_to_h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/mlp/dense_4h_to_h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/mlp/dense_h_to_4h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/mlp/dense_h_to_4h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/post_attention_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/39/post_attention_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/4/attention/dense/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/4/attention/dense/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/4/attention/query_key_value/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/4/attention/query_key_value/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/4/input_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/4/input_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/4/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/4/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/4/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/4/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/4/post_attention_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/4/post_attention_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/40/attention/dense/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/40/attention/dense/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/40/attention/query_key_value/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/40/attention/query_key_value/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/40/input_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/40/input_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/40/mlp/dense_4h_to_h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/40/mlp/dense_4h_to_h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/40/mlp/dense_h_to_4h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/40/mlp/dense_h_to_4h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/40/post_attention_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/40/post_attention_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/attention/dense/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/attention/dense/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/attention/query_key_value/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/attention/query_key_value/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/input_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/input_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/mlp/dense_4h_to_h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/mlp/dense_4h_to_h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/mlp/dense_h_to_4h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/mlp/dense_h_to_4h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/post_attention_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/41/post_attention_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/attention/dense/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/attention/dense/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/attention/query_key_value/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/attention/query_key_value/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/input_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/input_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/mlp/dense_4h_to_h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/mlp/dense_4h_to_h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/mlp/dense_h_to_4h/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/mlp/dense_h_to_4h/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/post_attention_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/42/post_attention_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/43/attention/dense/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/43/attention/dense/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/43/attention/query_key_value/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/43/attention/query_key_value/kernel": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/43/input_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/43/input_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/43/mlp/dense_4h_to_h/bias": "flax_model-00005-of-00005.msgpack",
"gpt_neox/layers/43/mlp/dense_4h_to_h/kernel": "flax_model-00005-of-00005.msgpack",
"gpt_neox/layers/43/mlp/dense_h_to_4h/bias": "flax_model-00005-of-00005.msgpack",
"gpt_neox/layers/43/mlp/dense_h_to_4h/kernel": "flax_model-00005-of-00005.msgpack",
"gpt_neox/layers/43/post_attention_layernorm/bias": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/43/post_attention_layernorm/scale": "flax_model-00004-of-00005.msgpack",
"gpt_neox/layers/5/attention/dense/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/5/attention/dense/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/5/attention/query_key_value/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/5/attention/query_key_value/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/5/input_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/5/input_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/5/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/5/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/5/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/5/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/5/post_attention_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/5/post_attention_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/attention/dense/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/attention/dense/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/attention/query_key_value/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/attention/query_key_value/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/input_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/input_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/post_attention_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/6/post_attention_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/attention/dense/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/attention/dense/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/attention/query_key_value/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/attention/query_key_value/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/input_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/input_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/post_attention_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/7/post_attention_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/attention/dense/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/attention/dense/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/attention/query_key_value/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/attention/query_key_value/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/input_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/input_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/post_attention_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/8/post_attention_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/attention/dense/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/attention/dense/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/attention/query_key_value/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/attention/query_key_value/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/input_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/input_layernorm/scale": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/mlp/dense_4h_to_h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/mlp/dense_4h_to_h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/mlp/dense_h_to_4h/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/mlp/dense_h_to_4h/kernel": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/post_attention_layernorm/bias": "flax_model-00001-of-00005.msgpack",
"gpt_neox/layers/9/post_attention_layernorm/scale": "flax_model-00001-of-00005.msgpack"
}
}