Duplicate from iamplus/gpt-neoxt-20b-v2

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,25 @@
+---
+license: bigscience-openrail-m
+datasets:
+- iamplus/Instruction_Tuning
+---
+Instruction Tuned GPT-NeoXT-20B model on Stanford Alpaca-2 Instruction Tuning dataset (outputs from ChatGPT) (52k data) using ***Colossal AI***
+
+**Base Model:** togethercomputer/GPT-NeoXT-Chat-Base-20B (not fine-tuned on feedback data)
+
+**Training Details :** 
+* Epochs: 5
+* Batch Size : 16 instantaneous per device x 1 gradient accumulation steps x 8 gpus = 128
+* Max Length : 1024
+* Weight Decay : 0
+* Learning Rate : 2e-5
+* Learning Rate Scheduler Type : Cosine
+* Number of warmup steps : 30
+* Machine : 8xA100 80GB
+
+**Dataset Details :**
+
+Dataset : iamplus/Instruction_Tuning
+
+Files : 
+* stanford_alpaca_it_v2.csv

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "outputs_alpaca_gpt_neo_v2",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_fast",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 44,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "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": "4.27.1"
+}

pytorch_model-00001-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b31eb1d28ed7b9b8e00c6a000d8a5e7c852941f917428396c38a98f6b0f28757
+size 9717703867

pytorch_model-00002-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93dd5c53e5e91159c8d8805b6a217979b4e46151321811f4482af943736f7ba1
+size 9690591743

pytorch_model-00003-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22ef1b043cfa5bfc6a864ca3ee01fb402bb55b2f0c7cdf108c3901a9850f615f
+size 9686371201

pytorch_model-00004-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd9ed49f9168e796dadb9759908351ca39012060e9aa6d98320d604f1e8907b
+size 9686370597

pytorch_model-00005-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cd7bd7ab122c83096d059fcfdc0a5a8b13a979f785078318310e351baa73439
+size 9690591871

pytorch_model-00006-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008bb5cb0c3cc495c5e6c42193ec58f66d690dc7f91e6016453342f929dd8c27
+size 9686371201

pytorch_model-00007-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60f7b14780cb3e0241c0a63626f0ece7eaa5c18ff432c893662fc4dbe6bcc1bd
+size 9686370597

pytorch_model-00008-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e873ef7da1a811468fb4691488e902f89846d8be9ffb24b20d8bc36e300d852d
+size 9690591871

pytorch_model-00009-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7dc7b5826c09b7c14f50f72de32f58c03192920c088a58dde289409ad863079
+size 4868088539

pytorch_model.bin.index.json

@@ -0,0 +1,671 @@
+{
+  "metadata": {
+    "total_size": 82241341680.0
+  },
+  "weight_map": {
+    "embed_out.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.final_layer_norm.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.final_layer_norm.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.10.attention.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.11.attention.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.attention.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.attention.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.attention.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.15.attention.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "gpt_neox.layers.16.attention.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.attention.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.attention.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.attention.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.20.attention.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "gpt_neox.layers.21.attention.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.attention.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.attention.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.attention.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.attention.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.26.attention.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "gpt_neox.layers.27.attention.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.attention.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.attention.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.30.attention.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.31.attention.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "gpt_neox.layers.32.attention.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.attention.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.attention.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.attention.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.attention.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "gpt_neox.layers.37.attention.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.37.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.attention.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.38.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.attention.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.39.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "gpt_neox.layers.40.attention.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.attention.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.42.attention.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.42.attention.dense.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.42.attention.dense.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.42.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.42.attention.query_key_value.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.42.attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.42.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.42.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.42.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.42.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.42.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.42.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.42.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "gpt_neox.layers.43.attention.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.attention.dense.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.attention.dense.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.attention.masked_bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.attention.query_key_value.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.attention.rotary_emb.inv_freq": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.input_layernorm.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.post_attention_layernorm.bias": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.43.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "gpt_neox.layers.5.attention.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.attention.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.attention.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.attention.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.attention.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "name_or_path": "EleutherAI/gpt-neox-20b",
+  "special_tokens_map_file": "/root/.cache/huggingface/transformers/d9026dc928c47ac2a72d46fea7db959acc4bacac2176bf32be5c331604b77d32.3ae9ae72462581d20e36bc528e9c47bb30cd671bb21add40ca0b24a0be9fac22",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}