初始化项目，由ModelHub XC社区提供模型

Model: h2oai/h2ogpt-oig-oasst1-256-6_9b
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 +1,124 @@
+---
+license: apache-2.0
+language:
+- en
+library_name: transformers
+inference: false
+thumbnail: https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
+tags:
+- gpt
+- llm
+- large language model
+- open-source
+datasets:
+- h2oai/h2ogpt-oig-oasst1-instruct-cleaned-v1
+---
+# h2oGPT Model Card
+## Summary
+
+H2O.ai's `h2ogpt-oig-oasst1-256-6_9b` is a 6.9 billion parameter instruction-following large language model licensed for commercial use.
+
+- Base model: [EleutherAI/pythia-6.9b](https://huggingface.co/EleutherAI/pythia-6.9b)
+- Fine-tuning dataset: [h2oai/h2ogpt-oig-oasst1-instruct-cleaned-v1](https://huggingface.co/datasets/h2oai/h2ogpt-oig-oasst1-instruct-cleaned-v1)
+- Data-prep and fine-tuning code: [H2O.ai Github](https://github.com/h2oai/h2ogpt)
+- Training logs: [zip](https://huggingface.co/h2oai/h2ogpt-oig-oasst1-256-6_9b/blob/main/pythia-6.9b.h2ogpt-oig-oasst1-instruct-cleaned-v1.json.1_epochs.5fc91911bc2bfaaf3b6c2de577c4b0ae45a07a4a.9.zip)
+
+## Usage
+
+To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers` and `accelerate` libraries installed.
+
+```bash
+pip install transformers==4.28.1
+pip install accelerate==0.18.0
+```
+
+```python
+import torch
+from transformers import pipeline
+
+generate_text = pipeline(model="h2oai/h2ogpt-oig-oasst1-256-6_9b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto", prompt_type='human_bot')
+
+res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
+print(res[0]["generated_text"])
+```
+
+Alternatively, if you prefer to not use `trust_remote_code=True` you can download [instruct_pipeline.py](https://huggingface.co/h2oai/h2ogpt-oig-oasst1-256-6_9b/blob/main/h2oai_pipeline.py),
+store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
+
+```python
+import torch
+from h2oai_pipeline import H2OTextGenerationPipeline
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-oig-oasst1-256-6_9b", padding_side="left")
+model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-oig-oasst1-256-6_9b", torch_dtype=torch.bfloat16, device_map="auto")
+generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer, prompt_type='human_bot')
+
+res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
+print(res[0]["generated_text"])
+```
+
+## Model Architecture
+
+```
+GPTNeoXForCausalLM(
+  (gpt_neox): GPTNeoXModel(
+    (embed_in): Embedding(50432, 4096)
+    (layers): ModuleList(
+      (0-31): 32 x GPTNeoXLayer(
+        (input_layernorm): LayerNorm((4096,), eps=1e-05, elementwise_affine=True)
+        (post_attention_layernorm): LayerNorm((4096,), eps=1e-05, elementwise_affine=True)
+        (attention): GPTNeoXAttention(
+          (rotary_emb): RotaryEmbedding()
+          (query_key_value): Linear(in_features=4096, out_features=12288, bias=True)
+          (dense): Linear(in_features=4096, out_features=4096, bias=True)
+        )
+        (mlp): GPTNeoXMLP(
+          (dense_h_to_4h): Linear(in_features=4096, out_features=16384, bias=True)
+          (dense_4h_to_h): Linear(in_features=16384, out_features=4096, bias=True)
+          (act): GELUActivation()
+        )
+      )
+    )
+    (final_layer_norm): LayerNorm((4096,), eps=1e-05, elementwise_affine=True)
+  )
+  (embed_out): Linear(in_features=4096, out_features=50432, bias=False)
+)
+```
+
+## Model Configuration
+
+```json
+GPTNeoXConfig {
+  "_name_or_path": "h2oai/h2ogpt-oig-oasst1-256-6_9b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "custom_pipelines": {
+    "text-generation": {
+      "impl": "h2oai_pipeline.H2OTextGenerationPipeline",
+      "pt": "AutoModelForCausalLM"
+    }
+  },
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50432
+}
+
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "EleutherAI/pythia-6.9b",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "custom_pipelines": {
+    "text-generation": {
+      "impl": "h2oai_pipeline.H2OTextGenerationPipeline",
+      "pt": "AutoModelForCausalLM"
+    }
+  },
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.28.0.dev0",
+  "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": "4.28.0.dev0"
+}

h2oai_pipeline.py

@@ -0,0 +1,30 @@
+from transformers import TextGenerationPipeline
+from transformers.pipelines.text_generation import ReturnType
+
+human = "<human>:"
+bot = "<bot>:"
+
+# human-bot interaction like OIG dataset
+prompt = """{human} {instruction}
+{bot}""".format(
+    human=human,
+    instruction="{instruction}",
+    bot=bot,
+)
+
+
+class H2OTextGenerationPipeline(TextGenerationPipeline):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+    def preprocess(self, prompt_text, prefix="", handle_long_generation=None, **generate_kwargs):
+        prompt_text = prompt.format(instruction=prompt_text)
+        return super().preprocess(prompt_text, prefix=prefix, handle_long_generation=handle_long_generation,
+                                  **generate_kwargs)
+
+    def postprocess(self, model_outputs, return_type=ReturnType.FULL_TEXT, clean_up_tokenization_spaces=True):
+        records = super().postprocess(model_outputs, return_type=return_type,
+                                      clean_up_tokenization_spaces=clean_up_tokenization_spaces)
+        for rec in records:
+            rec['generated_text'] = rec['generated_text'].split(bot)[1].strip().split(human)[0].strip()
+        return records

pythia-6.9b.h2ogpt-oig-oasst1-instruct-cleaned-v1.json.1_epochs.5fc91911bc2bfaaf3b6c2de577c4b0ae45a07a4a.9.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6bcf329115bd0ba38553ded3cc6f483e52fd551106c80d8ff50e63a0f8445f0
+size 156827326

pytorch_model-00001-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3fbeec624a1637c9282188593cc28115b0ff5768ed465042b2542c10f3009ca
+size 5028171302

pytorch_model-00002-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8d5ff89e8974e6213652fb68e1e5b9b44b7f45d8319bab7ceeaa47e893dc7f
+size 5017761129

pytorch_model-00003-of-00003.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fc4f3ef19bc0998fb1953b6556733440ff9f7f2bb0599ba098c504cf9204ec
+size 3803055858

pytorch_model.bin.index.json

@@ -0,0 +1,491 @@
+{
+  "metadata": {
+    "total_size": 13731383360.0
+  },
+  "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-00002-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
+    "gpt_neox.layers.12.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.16.attention.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-00003-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
+    "gpt_neox.layers.24.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.3.attention.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-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
+    "gpt_neox.layers.4.attention.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 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}