h2oai/h2ogpt-oasst1-512-20b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: h2oai/h2ogpt-oasst1-512-20b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-21 21:22:29 +08:00
commit f23987ab40
20 changed files with 101531 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
.gitattributes vendored Normal file
View File

@@ -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

175
README.md Normal file
View File

@@ -0,0 +1,175 @@
---
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/openassistant_oasst1
- h2oai/openassistant_oasst1_h2ogpt
---
# h2oGPT Model Card
## Summary
H2O.ai's `h2ogpt-oasst1-512-20b` is a 20 billion parameter instruction-following large language model licensed for commercial use.
- Base model: [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b)
- Fine-tuning dataset: [h2oai/openassistant_oasst1](https://huggingface.co/datasets/h2oai/openassistant_oasst1) and [h2oai/openassistant_oasst1_h2ogpt](https://huggingface.co/datasets/h2oai/openassistant_oasst1_h2ogpt)
- Data-prep and fine-tuning code: [H2O.ai GitHub](https://github.com/h2oai/h2ogpt)
- Training logs: [zip](https://huggingface.co/h2oai/h2ogpt-oasst1-512-20b/blob/main/gpt-neox-20b.openassistant_oasst1.json.6.0_epochs.5a14ea8b3794c0d60476fc262d0a297f98dd712d.1013.zip) and [zip](https://huggingface.co/h2oai/h2ogpt-oasst1-512-20b/blob/main/h2ogpt-oasst1-512-20b.h2oaiopenassistant_oasst1_h2ogpt.2_epochs.fcaae7ef70600de8c97c9b38cb3f0075467cdad1.3.zip)
## Chatbot
- Run your own chatbot: [H2O.ai GitHub](https://github.com/h2oai/h2ogpt)
[![H2O.ai GitHub](https://user-images.githubusercontent.com/6147661/232930822-e7170e4d-8aa1-4f7a-ad70-ece9cdd8b0cb.png)](https://github.com/h2oai/h2ogpt)
## 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-oasst1-512-20b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")
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-oasst1-512-20b/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-oasst1-512-20b", padding_side="left")
model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-oasst1-512-20b", torch_dtype=torch.bfloat16, device_map="auto")
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)
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, 6144)
(layers): ModuleList(
(0-43): 44 x GPTNeoXLayer(
(input_layernorm): LayerNorm((6144,), eps=1e-05, elementwise_affine=True)
(post_attention_layernorm): LayerNorm((6144,), eps=1e-05, elementwise_affine=True)
(attention): GPTNeoXAttention(
(rotary_emb): RotaryEmbedding()
(query_key_value): Linear(in_features=6144, out_features=18432, bias=True)
(dense): Linear(in_features=6144, out_features=6144, bias=True)
)
(mlp): GPTNeoXMLP(
(dense_h_to_4h): Linear(in_features=6144, out_features=24576, bias=True)
(dense_4h_to_h): Linear(in_features=24576, out_features=6144, bias=True)
(act): FastGELUActivation()
)
)
)
(final_layer_norm): LayerNorm((6144,), eps=1e-05, elementwise_affine=True)
)
(embed_out): Linear(in_features=6144, out_features=50432, bias=False)
)
```
## Model Configuration
```json
GPTNeoXConfig {
"_name_or_path": "h2oai/h2ogpt-oasst1-512-20b",
"architectures": [
"GPTNeoXForCausalLM"
],
"attention_probs_dropout_prob": 0,
"bos_token_id": 0,
"custom_pipeline": {
"text-generation": {
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
"pt": "AutoModelForCausalLM"
}
},
"custom_pipelines": {
"text-generation": {
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
"pt": "AutoModelForCausalLM"
}
},
"eos_token_id": 0,
"hidden_act": "gelu_fast",
"hidden_dropout_prob": 0,
"hidden_size": 6144,
"initializer_range": 0.02,
"intermediate_size": 24576,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 64,
"num_hidden_layers": 44,
"rotary_emb_base": 10000,
"rotary_pct": 0.25,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.1",
"use_cache": true,
"use_parallel_residual": true,
"vocab_size": 50432
}
```
## Model Validation
Model validation results using [EleutherAI lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness).
[eval source code](https://github.com/h2oai/h2ogpt/issues/35#issuecomment-1521119301)
| Task |Version| Metric |Value | |Stderr|
|-------------|------:|--------|-----:|---|-----:|
|hellaswag | 0|acc |0.5419|± |0.0050|
| | |acc_norm|0.7259|± |0.0045|
|boolq | 1|acc |0.7125|± |0.0079|
|piqa | 0|acc |0.7742|± |0.0098|
| | |acc_norm|0.7775|± |0.0097|
|openbookqa | 0|acc |0.2800|± |0.0201|
| | |acc_norm|0.4000|± |0.0219|
|arc_challenge| 0|acc |0.3993|± |0.0143|
| | |acc_norm|0.4420|± |0.0145|
|winogrande | 0|acc |0.6614|± |0.0133|
|arc_easy | 0|acc |0.7327|± |0.0091|
| | |acc_norm|0.6894|± |0.0095|
## Disclaimer
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.

39
config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"_name_or_path": "h2oai/h2ogpt-oasst1-512-20b",
"architectures": [
"GPTNeoXForCausalLM"
],
"attention_probs_dropout_prob": 0,
"bos_token_id": 0,
"custom_pipeline": {
"text-generation": {
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
"pt": "AutoModelForCausalLM"
}
},
"custom_pipelines": {
"text-generation": {
"impl": "h2oai_pipeline.H2OTextGenerationPipeline",
"pt": "AutoModelForCausalLM"
}
},
"eos_token_id": 0,
"hidden_act": "gelu_fast",
"hidden_dropout_prob": 0,
"hidden_size": 6144,
"initializer_range": 0.02,
"intermediate_size": 24576,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 64,
"num_hidden_layers": 44,
"rotary_emb_base": 10000,
"rotary_pct": 0.25,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.28.1",
"use_cache": true,
"use_parallel_residual": true,
"vocab_size": 50432
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 0,
"eos_token_id": 0,
"transformers_version": "4.28.1"
}

3
gpt-neox-20b.openassistant_oasst1.json.6.0_epochs.5a14ea8b3794c0d60476fc262d0a297f98dd712d.1013.zip Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f82e8b5514756068f3f497f20396328fcd87ff610c97cc1b9aa6e4bf3c79b803
size 447618892

30
h2oai_pipeline.py Normal file
View File

@@ -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

3
h2ogpt-oasst1-512-20b.h2oaiopenassistant_oasst1_h2ogpt.2_epochs.fcaae7ef70600de8c97c9b38cb3f0075467cdad1.3.zip Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:263265772d224d344f41d7d246ad82db8e32c4931cf70f14743bee24739e0f24
size 511984220

3
pytorch_model-00001-of-00009.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7dc9f7e5c854cd545b901d2fb97b9f9f72f71d105dabdac967fee44dd1d8be85
size 4869350099

3
pytorch_model-00002-of-00009.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1a7940f5372a476f93ace4511fd63f1c26b7e3d5844ad459e4f951311bf9fe2e
size 4857893019

3
pytorch_model-00003-of-00009.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1db198acba0f804c80b30baea152c91aec8d59f57b456a1be84e6852e7ce7cf2
size 4853684773

3
pytorch_model-00004-of-00009.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8e739e2b724b30d8cdd4b1ddb1dd77536153f0da4ce9727d269d6b91e27e074a
size 4853684001

3
pytorch_model-00005-of-00009.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:979f6e44342065c2775dfcff91b79163d23c9b6b620d9d8e5d74860782b94af9
size 4857893083

3
pytorch_model-00006-of-00009.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ea72ab7af0e35f2f66ac70c2a1b16d76196b9f1a2597f414340c47c419925d97
size 4853684773

3
pytorch_model-00007-of-00009.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9609641cae12c782c208ce7b5bd0889dee0d3db448d9ca75abc0a5de31242ba0
size 4853684001

3
pytorch_model-00008-of-00009.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2a8c708b2f10a43f67321997b8cfb743ec0ff3e6b0927785b6cb447a9da47786
size 4857893083

3
pytorch_model-00009-of-00009.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f88d774345f067d9f5221463772bac423435699883ca7a2b13dc4ece8c59eef8
size 2436145827

671
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,671 @@
{
"metadata": {
"total_size": 41132206232.0
},
"weight_map": {
"embed_out.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.embed_in.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.final_layer_norm.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.final_layer_norm.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.10.attention.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.11.attention.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.attention.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.attention.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.attention.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.15.attention.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
"gpt_neox.layers.16.attention.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.attention.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.attention.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.attention.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.20.attention.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
"gpt_neox.layers.21.attention.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.attention.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.attention.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.attention.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.attention.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.26.attention.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
"gpt_neox.layers.27.attention.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.attention.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.attention.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.30.attention.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.31.attention.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
"gpt_neox.layers.32.attention.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.32.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.attention.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.33.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.attention.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.attention.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.mlp.dense_4h_to_h.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.attention.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.attention.dense.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.attention.dense.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.attention.masked_bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.attention.query_key_value.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.attention.query_key_value.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.attention.rotary_emb.inv_freq": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.input_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.36.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.36.mlp.dense_h_to_4h.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.post_attention_layernorm.bias": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
"gpt_neox.layers.37.attention.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.37.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.attention.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.38.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.attention.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.39.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
"gpt_neox.layers.40.attention.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.attention.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.attention.dense.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.attention.dense.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.attention.query_key_value.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.attention.query_key_value.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.mlp.dense_4h_to_h.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.mlp.dense_h_to_4h.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.42.attention.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.42.attention.dense.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.42.attention.dense.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.42.attention.masked_bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.42.attention.query_key_value.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.42.attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.42.attention.rotary_emb.inv_freq": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.42.input_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.42.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.42.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.42.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.42.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.42.post_attention_layernorm.bias": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
"gpt_neox.layers.43.attention.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.attention.dense.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.attention.dense.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.attention.masked_bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.attention.query_key_value.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.attention.query_key_value.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.attention.rotary_emb.inv_freq": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.input_layernorm.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.mlp.dense_4h_to_h.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.mlp.dense_h_to_4h.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.post_attention_layernorm.bias": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.43.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
"gpt_neox.layers.5.attention.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.attention.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.attention.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.attention.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.attention.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00002-of-00009.bin",
"gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin"
}
}

5
special_tokens_map.json Normal file
View File

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

100529
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

9
tokenizer_config.json Normal file
View File

@@ -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|>"
}