初始化项目，由ModelHub XC社区提供模型

Model: nlpai-lab/kullm-polyglot-12.8b-v2
Source: Original Platform

.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 +1,34 @@
+---
+license: apache-2.0
+language:
+- ko
+---
+# KULLM-Polyglot-12.8B-v2
+
+This model is a fine-tuned version of [EleutherAI/polyglot-ko-12.8b](https://huggingface.co/EleutherAI/polyglot-ko-12.8b) on a KULLM v2 
+
+Detail Codes are available at [KULLM Github Repository](https://github.com/nlpai-lab/KULLM)
+
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+
+- learning_rate: 3e-4
+- train_batch_size: 6
+- seed: 42
+- distributed_type: multi-GPU (A100 80G)
+- num_devices: 4
+- gradient_accumulation_steps: 21.3
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8.0
+
+### Framework versions
+
+- Transformers 4.28.1
+- Pytorch 2.0.0+cu117
+- Datasets 2.11.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/data/persuade/01_KuAlpaca/models/lora-alpaca-merged-ep5",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 20480,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_steps": "global_step301000",
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.5,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.2",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 30080
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.29.2"
+}

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b4c9e0e22f14ad295e4ffebbb2dd5469584dfb6ed498411f03e2030fd0b133
+size 10024193402

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9214f433e6ab8aa5c02a620deac77318dd50546c363cbc11ee21449442250a94
+size 9925899395

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c9dbe3f451f311cd09518f68b66c9ed7656d5f1040028fe9e32ae4f09ada46
+size 6005109272

pytorch_model.bin.index.json

@@ -0,0 +1,611 @@
+{
+  "metadata": {
+    "total_size": 25808184400.0
+  },
+  "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.bias": "pytorch_model-00001-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.masked_bias": "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.bias": "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.masked_bias": "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.bias": "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.masked_bias": "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.bias": "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.masked_bias": "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-00001-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-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.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.15.attention.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00001-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-00001-of-00003.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.16.attention.bias": "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.masked_bias": "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.bias": "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.masked_bias": "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.bias": "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.masked_bias": "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.bias": "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.masked_bias": "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.bias": "pytorch_model-00001-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.masked_bias": "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.bias": "pytorch_model-00002-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.masked_bias": "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.bias": "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.masked_bias": "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.bias": "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.masked_bias": "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.bias": "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.masked_bias": "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-00002-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-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.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-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.masked_bias": "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.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.31.attention.bias": "pytorch_model-00002-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.masked_bias": "pytorch_model-00002-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-00002-of-00003.bin",
+    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00002-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-00002-of-00003.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.32.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-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.masked_bias": "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.bias": "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.masked_bias": "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.bias": "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.masked_bias": "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.bias": "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.masked_bias": "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.bias": "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.masked_bias": "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.bias": "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.masked_bias": "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 +1,11 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,7 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}