Upload GPTNeoXForCausalLM

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/fsx/ckpts/7b_tok=neox_data=pilev2-recontam_lower-code_bs=8m_tp=4_pp=1_init=wang-small-init/global_step69000_hf",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 16,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50432
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.27.4"
+}

pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d92cc51dd745fe03be2e5509c1b719676204c857bdd37cec5bf046d41225342
+size 9780618427

pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5a52081181cc79abae6d9ea1204f8cc36172e86fef69d28aaf5e0f81497d7cb
+size 9766089215

pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebcf7f3aacf746dd5a85995acbc50a17e3a43f9a0d5702635ad40a7a1d99ed6c
+size 9749285761

pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f7dc1e04951c32a121a40cffa764f892eca8744a151712737c3fdea37094770
+size 2447551184

pytorch_model.bin.index.json

@@ -0,0 +1,251 @@
+{
+  "metadata": {
+    "total_size": 31508579392.0
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.10.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.11.attention.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00004.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "gpt_neox.layers.5.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00004.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin"
+  }
+}