README.md

---
base_model: Kyleyee/Qwen2.5-1.5B-sft-hh-3e
library_name: transformers
model_name: Qwen2.5-1.5B-drpo-lora-flip-hh
tags:
- generated_from_trainer
- drpo
- trl
licence: license
---

# Model Card for Qwen2.5-1.5B-drpo-lora-flip-hh

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).
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="Eehan/Qwen2.5-1.5B-drpo-lora-flip-hh", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])
```

## Training procedure

 


This model was trained with DRPO, a method introduced in [Doubly Robust Alignment for Large Language Models](https://huggingface.co/papers/2506.01183).

### Framework versions

- TRL: 0.19.1
- Transformers: 4.54.0
- Pytorch: 2.7.1
- Datasets: 4.0.0
- Tokenizers: 0.21.2

## Citations

Cite DRPO as:

```bibtex
@article{xu2024doubly,
    title        = {{Doubly Robust Alignment for Large Language Models}},
    author       = {Xu, Erhan and Ye, Kai and Zhou, Hongyi and Zhu, Luhan and Quinzan, Francesco and Shi, Chengchun},
    year         = 2025,
    journal      = {arXiv preprint arXiv:2506.01183}
}
```

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}}
}
```