---
base_model: vectorzhou/Qwen2.5-1.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT
datasets: OpenRLHF/prompt-collection-v0.1
library_name: transformers
model_name: Qwen2.5-1.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT-prompt-collection-v0.1-NashMDPG-lora
tags:
- generated_from_trainer
- text-generation
- fine-tuned
- trl
- nash-md
licence: license
---

# Model Card for Qwen2.5-1.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT-prompt-collection-v0.1-NashMDPG-lora

This model is a fine-tuned version of [vectorzhou/Qwen2.5-1.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT](https://huggingface.co/vectorzhou/Qwen2.5-1.5B-Instruct-SFT-OpenHermes-2.5-Standard-SFT) on the [OpenRLHF/prompt-collection-v0.1](https://huggingface.co/datasets/OpenRLHF/prompt-collection-v0.1) 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="vectorzhou/Qwen2.5-1.5B-Instruct-SFT-OpenHerm-llection-v0.1-NashMDPG-lora-0605154608-epoch-10", 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/zhourunlongvector/nlhf/runs/7mdxr4x4) 


This model was trained with Nash-MD, a method introduced in [Nash Learning from Human Feedback](https://huggingface.co/papers/2312.00886).

### Framework versions

- TRL: 0.13.0
- Transformers: 4.48.0
- Pytorch: 2.2.1
- Datasets: 3.2.0
- Tokenizers: 0.21.0

## Citations

Cite Nash-MD as:

```bibtex
@inproceedings{munos2024nash,
    title        = {Nash Learning from Human Feedback},
    author       = {R{'{e}}mi Munos and Michal Valko and Daniele Calandriello and Mohammad Gheshlaghi Azar and Mark Rowland and Zhaohan Daniel Guo and Yunhao Tang and Matthieu Geist and Thomas Mesnard and C{\^{o}}me Fiegel and Andrea Michi and Marco Selvi and Sertan Girgin and Nikola Momchev and Olivier Bachem and Daniel J. Mankowitz and Doina Precup and Bilal Piot},
    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=Y5AmNYiyCQ}
}
```

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}}
}
```