NYTK/PULI-GPT-3SX
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: NYTK/PULI-GPT-3SX
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-04 12:57:18 +08:00
commit 3a807cf830
16 changed files with 150588 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

72
README.md Normal file
View File

@@ -0,0 +1,72 @@
---
language:
- hu
tags:
- text-generation
- puli
license: cc-by-nc-4.0
widget:
- text: Elmesélek egy történetet a nyelvtechnológiáról.
---
# PULI 3SX base (6.85 billion parameter)
For further details, see [our demo site](https://puli.nytud.hu/puli-3sx).
- Hungarian GPT-NeoX model (6.7 billion parameter)
- Trained with EleutherAI's GPT-NeoX [github](https://github.com/EleutherAI/gpt-neox)
- Dataset: 36.3 billion words
- Checkpoint: 150 000 steps
## Limitations
- max_seq_length = 2048
## Citation
If you use this model, please cite the following paper:
```
@inproceedings {yang-puli,
title = {Jönnek a nagyok! BERT-Large, GPT-2 és GPT-3 nyelvmodellek magyar nyelvre},
booktitle = {XIX. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2023)},
year = {2023},
publisher = {Szegedi Tudományegyetem, Informatikai Intézet},
address = {Szeged, Hungary},
author = {Yang, Zijian Győző and Dodé, Réka and Ferenczi, Gergő and Héja, Enikő and Jelencsik-Mátyus, Kinga and Kőrös, Ádám and Laki, László János and Ligeti-Nagy, Noémi and Vadász, Noémi and Váradi, Tamás},
pages = {247--262}
}
```
## Usage
```python
from transformers import GPTNeoXForCausalLM, AutoTokenizer
model = GPTNeoXForCausalLM.from_pretrained("NYTK/PULI-GPT-3SX")
tokenizer = AutoTokenizer.from_pretrained("NYTK/PULI-GPT-3SX")
prompt = "Elmesélek egy történetet a nyelvtechnológiáról."
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
gen_tokens = model.generate(
input_ids,
do_sample=True,
temperature=0.9,
max_length=100,
)
gen_text = tokenizer.batch_decode(gen_tokens)[0]
print(gen_text)
```
## Usage with pipeline
```python
from transformers import pipeline, GPTNeoXForCausalLM, AutoTokenizer
model = GPTNeoXForCausalLM.from_pretrained("NYTK/PULI-GPT-3SX")
tokenizer = AutoTokenizer.from_pretrained("NYTK/PULI-GPT-3SX")
prompt = "Elmesélek egy történetet a nyelvtechnológiáról."
generator = pipeline(task="text-generation", model=model, tokenizer=tokenizer)
print(generator(prompt)[0]["generated_text"])
```

30
config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"_name_or_path": "NYTK/PULI-GPT-3SX",
"architectures": [
"GPTNeoXForCausalLM"
],
"attention_bias": true,
"attention_dropout": 0.0,
"bos_token_id": 7,
"classifier_dropout": 0.1,
"eos_token_id": 7,
"hidden_act": "gelu",
"hidden_dropout": 0.0,
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 16384,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 2048,
"model_type": "gpt_neox",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"rope_scaling": null,
"rotary_emb_base": 10000,
"rotary_pct": 1.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.37.0",
"use_cache": true,
"use_parallel_residual": false,
"vocab_size": 50048
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 7,
"eos_token_id": 7,
"transformers_version": "4.37.0"
}

49721
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2737598a331f6a7e8b3979e50b4f720bb05717047ad510dd64fed357e8e138e4
size 4974649592

3
model-00002-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d885cc214e96df30a7193295f19d56406ec78f78000ef074d6e6fc3d7b5fcea6
size 4967383992

3
model-00003-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f449441d6b18e70acef0b8cc15e2c3685aab33d147bc9076d2317cf433186c66
size 3766324912

395
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,395 @@
{
"metadata": {
"total_size": 13708312576
},
"weight_map": {
"embed_out.weight": "model-00003-of-00003.safetensors",
"gpt_neox.embed_in.weight": "model-00001-of-00003.safetensors",
"gpt_neox.final_layer_norm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.final_layer_norm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.12.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.12.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.12.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.12.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.12.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.12.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.20.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.20.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.20.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.20.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.20.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.20.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.23.attention.dense.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.23.attention.dense.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.23.attention.query_key_value.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.23.attention.query_key_value.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.23.input_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.23.post_attention_layernorm.bias": "model-00002-of-00003.safetensors",
"gpt_neox.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"gpt_neox.layers.24.attention.dense.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.24.attention.dense.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.24.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.24.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.24.input_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.24.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.attention.dense.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.attention.dense.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.input_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.attention.dense.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.attention.dense.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.input_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.attention.dense.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.attention.dense.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.input_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.attention.dense.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.attention.dense.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.input_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.attention.dense.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.attention.dense.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.input_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.30.attention.dense.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.30.attention.dense.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.30.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.30.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.30.input_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.30.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.attention.dense.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.attention.dense.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.attention.query_key_value.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.attention.query_key_value.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.input_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.post_attention_layernorm.bias": "model-00003-of-00003.safetensors",
"gpt_neox.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00003.safetensors",
"gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors"
}
}

3
pytorch_model-00001-of-00002.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de8edfde9c1db8982c14ea74f225b1bc60111000ed2cbbdc0cab7b7c96e20966
size 9908539158

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e2b1e371d8684c63980405cb290be154bd33bfcb527941b008bd3383109a813e
size 3934161816

491
pytorch_model.bin.index.json Normal file
View File

@@ -0,0 +1,491 @@
{
"metadata": {
"total_size": 13842534464
},
"weight_map": {
"embed_out.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.embed_in.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.23.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.24.attention.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.attention.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.attention.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.attention.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.attention.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.attention.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.30.attention.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.attention.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
"gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
"gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin"
}
}

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

99767
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

33
tokenizer_config.json Normal file
View File

@@ -0,0 +1,33 @@
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"name_or_path": "/home/yanggy/gpt3/convert/gpt-neox/checkpoints",
"pad_token": null,
"special_tokens_map_file": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long