70 lines
2.6 KiB
Markdown
70 lines
2.6 KiB
Markdown
|
---
|
||
|
|
base_model: Kyleyee/Qwen2.5-1.5B-sft-hh-3e
|
||
|
|
datasets: Kyleyee/train_data_Helpful_drdpo_preference
|
||
|
|
library_name: transformers
|
||
|
|
model_name: CPO_hh-seed4
|
||
|
|
tags:
|
||
|
|
- generated_from_trainer
|
||
|
|
- trl
|
||
|
|
- cpo
|
||
|
|
licence: license
|
||
|
|
---
|
||
|
|
|
||
|
|
# Model Card for CPO_hh-seed4
|
||
|
|
|
||
|
|
This model is a fine-tuned version of [Kyleyee/Qwen2.5-1.5B-sft-hh-3e](https://huggingface.co/Kyleyee/Qwen2.5-1.5B-sft-hh-3e) on the [Kyleyee/train_data_Helpful_drdpo_preference](https://huggingface.co/datasets/Kyleyee/train_data_Helpful_drdpo_preference) dataset.
|
||
|
|
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="Kyleyee/CPO_hh-seed4", 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/qixy25-tsinghua-university/huggingface/runs/782jidxy)
|
||
|
|
|
||
|
|
|
||
|
|
This model was trained with CPO, a method introduced in [Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation](https://huggingface.co/papers/2401.08417).
|
||
|
|
|
||
|
|
### Framework versions
|
||
|
|
|
||
|
|
- TRL: 0.16.0.dev0
|
||
|
|
- Transformers: 4.49.0
|
||
|
|
- Pytorch: 2.6.0+cu126
|
||
|
|
- Datasets: 3.3.2
|
||
|
|
- Tokenizers: 0.21.0
|
||
|
|
|
||
|
|
## Citations
|
||
|
|
|
||
|
|
Cite CPO as:
|
||
|
|
|
||
|
|
```bibtex
|
||
|
|
@inproceedings{xu2024contrastive,
|
||
|
|
title = {{Contrastive Preference Optimization: Pushing the Boundaries of LLM Performance in Machine Translation}},
|
||
|
|
author = {Haoran Xu and Amr Sharaf and Yunmo Chen and Weiting Tan and Lingfeng Shen and Benjamin Van Durme and Kenton Murray and Young Jin Kim},
|
||
|
|
year = 2024,
|
||
|
|
booktitle = {Forty-first International Conference on Machine Learning, {ICML} 2024, Vienna, Austria, July 21-27, 2024},
|
||
|
|
publisher = {OpenReview.net},
|
||
|
|
url = {https://openreview.net/forum?id=51iwkioZpn}
|
||
|
|
}
|
||
|
|
```
|
||
|
|
|
||
|
|
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 Gallouédec},
|
||
|
|
year = 2020,
|
||
|
|
journal = {GitHub repository},
|
||
|
|
publisher = {GitHub},
|
||
|
|
howpublished = {\url{https://github.com/huggingface/trl}}
|
||
|
|
}
|
||
|
|
```
|