Add cleanrl/EleutherAI_pythia-6.9b-deduped__sft__tldr-main checkpoint

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "vwxyzjn/EleutherAI_pythia-6.9b-deduped__sft__tldr",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50432
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "transformers_version": "4.33.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0039f05c4c72acd7aa8d06974136681d85346f533a22bf103bfe1fe705d563
+size 4977795456

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f866bc605c03879ef1adbea7d2326e47e6bab74020522e32cd9468f17f91b2f9
+size 9955611669

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f54de6520061008d292474c4cb245ee9c9ed9968f241efed7c155e38b32159
+size 9934789356

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b9884add9f5931da921a02fb3b4ff49671fa8c61e5e5e60a0e9c4923d0b0eaa
+size 7538955833

pytorch_model.bin.index.json

@@ -0,0 +1,427 @@
+{
+  "metadata": {
+    "total_size": 27429210112
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "[PAD]",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "padding_side": "right",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}