README.md

---
base_model: Qwen/Qwen2.5-0.5B-Instruct
library_name: transformers
model_name: Qwen2.5-0.5B-DPO
tags:
- generated_from_trainer
- trl
- dpo
licence: license
---

# Model Card for Qwen2.5-0.5B-DPO

Fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) to generate YouTube titles based on my preferences. It was trained using [TRL](https://github.com/huggingface/trl).

[Video link](https://youtu.be/bbVoDXoPrPM) <br>
[Blog link](https://shawhin.medium.com/fine-tuning-llms-on-human-feedback-rlhf-dpo-1c693dbc4cbf) <br>
[GitHub Repo](https://github.com/ShawhinT/YouTube-Blog/tree/main/LLMs/dpo) <br>
[Training Dataset](https://huggingface.co/datasets/shawhin/youtube-titles-dpo) 

## Quick start

```python
from transformers import pipeline

video_idea = "independent component analysis intro"
prompt = f"<|im_start|>user\n{video_idea}<|im_end|>\n<|im_start|>assistant\n"

generator = pipeline("text-generation", model="shawhin/Qwen2.5-0.5B-DPO", device="cuda")
outputs = generator(prompt, max_length=100, truncation=True, num_return_sequences=1, temperature=0.7)
print(outputs[0]['generated_text'])
```

## Training procedure

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: 0.15.1
- Transformers: 4.48.0
- Pytorch: 2.6.0
- Datasets: 3.3.1
- Tokenizers: 0.21.0

## 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 Gallouédec},
	year         = 2020,
	journal      = {GitHub repository},
	publisher    = {GitHub},
	howpublished = {\url{https://github.com/huggingface/trl}}
}
```