初始化项目，由ModelHub XC社区提供模型
Model: camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered-DPO Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal file
@@ -0,0 +1,35 @@
|
||||
*.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
|
||||
*.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
|
||||
69
README.md
Normal file
69
README.md
Normal file
@@ -0,0 +1,69 @@
|
||||
---
|
||||
base_model: Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered
|
||||
library_name: transformers
|
||||
model_name: sfm-sft_dolci_mcqa_instruct_filtered-DPO
|
||||
tags:
|
||||
- generated_from_trainer
|
||||
- trl
|
||||
- dpo
|
||||
licence: license
|
||||
---
|
||||
|
||||
# Model Card for sfm-sft_dolci_mcqa_instruct_filtered-DPO
|
||||
|
||||
This model is a fine-tuned version of [Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered](https://huggingface.co/Kyle1668/sfm-sft_dolci_mcqa_instruct_filtered).
|
||||
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||||
|
||||
## Quick start
|
||||
|
||||
```python
|
||||
from transformers import pipeline
|
||||
|
||||
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
||||
generator = pipeline("text-generation", model="camgeodesic/sfm-sft_dolci_mcqa_instruct_filtered-DPO", device="cuda")
|
||||
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
||||
print(output["generated_text"])
|
||||
```
|
||||
|
||||
## Training procedure
|
||||
|
||||
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/geodesic/SFM%20-%20DPO/runs/7ezquuoo)
|
||||
|
||||
|
||||
This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
|
||||
|
||||
### Framework versions
|
||||
|
||||
- TRL: 0.26.1
|
||||
- Transformers: 4.57.3
|
||||
- Pytorch: 2.9.1+cu128
|
||||
- Datasets: 4.4.1
|
||||
- Tokenizers: 0.22.1
|
||||
|
||||
## Citations
|
||||
|
||||
Cite DPO as:
|
||||
|
||||
```bibtex
|
||||
@inproceedings{rafailov2023direct,
|
||||
title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
|
||||
author = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
|
||||
year = 2023,
|
||||
booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
|
||||
url = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
|
||||
editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
|
||||
}
|
||||
```
|
||||
|
||||
Cite TRL as:
|
||||
|
||||
```bibtex
|
||||
@misc{vonwerra2022trl,
|
||||
title = {{TRL: Transformer Reinforcement Learning}},
|
||||
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
|
||||
year = 2020,
|
||||
journal = {GitHub repository},
|
||||
publisher = {GitHub},
|
||||
howpublished = {\url{https://github.com/huggingface/trl}}
|
||||
}
|
||||
```
|
||||
9
chat_template.jinja
Normal file
9
chat_template.jinja
Normal file
@@ -0,0 +1,9 @@
|
||||
{{ bos_token }}{% for message in messages %}{% if message['role'] == 'system' %}{{ '<|system|>
|
||||
' + message['content'] + '
|
||||
' }}{% elif message['role'] == 'user' %}{{ '<|user|>
|
||||
' + message['content'] + '
|
||||
' }}{% elif message['role'] == 'assistant' %}{% if not loop.last %}{{ '<|assistant|>
|
||||
' + message['content'] + eos_token + '
|
||||
' }}{% else %}{{ '<|assistant|>
|
||||
' + message['content'] + eos_token }}{% endif %}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<|assistant|>
|
||||
' }}{% endif %}{% endfor %}
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"architectures": [
|
||||
"GPTNeoXForCausalLM"
|
||||
],
|
||||
"attention_bias": true,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"classifier_dropout": 0.1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 0,
|
||||
"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": 16384,
|
||||
"model_type": "gpt_neox",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"pad_token_id": 0,
|
||||
"partial_rotary_factor": 0.25,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"rotary_emb_base": 10000.0,
|
||||
"rotary_pct": 0.25,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.3",
|
||||
"use_cache": true,
|
||||
"use_parallel_residual": true,
|
||||
"vocab_size": 50304
|
||||
}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": [
|
||||
0,
|
||||
2
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.57.3"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bee7798069977ae03ba1c56da32a49ee3fbd20ccdaf09eb0d3ad0c8b0decc0dd
|
||||
size 4976746880
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c2c8698b0974cb192dc532c98f3e86db999b0d181197dc978f44fc857984431
|
||||
size 4967384136
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ad57206a0b58813acce5c192c9ad41beb0e6c21f78bb858829fc658968135f78
|
||||
size 3768422160
|
||||
396
model.safetensors.index.json
Normal file
396
model.safetensors.index.json
Normal file
@@ -0,0 +1,396 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_parameters": 6856253440,
|
||||
"total_size": 13712506880
|
||||
},
|
||||
"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"
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|endoftext|>",
|
||||
"unk_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
250586
tokenizer.json
Normal file
250586
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
223
tokenizer_config.json
Normal file
223
tokenizer_config.json
Normal file
@@ -0,0 +1,223 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|padding|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"50254": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50255": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50256": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50257": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50258": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50259": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50260": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50261": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50262": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50263": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50264": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50265": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50266": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50267": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50268": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50269": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50270": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50271": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50272": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50273": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50274": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50275": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50276": {
|
||||
"content": " ",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"50277": {
|
||||
"content": "XXF",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"extra_special_tokens": {},
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPTNeoXTokenizer",
|
||||
"unk_token": "<|endoftext|>"
|
||||
}
|
||||
3
training_args.bin
Normal file
3
training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c8c790ccce2137449d63238fd4dd7f87d061ce75cb3d10486eee373192dfba85
|
||||
size 8209
|
||||
Reference in New Issue
Block a user