---
base_model: Audreygyj/pythia-160m-sft-HH-2-merge
datasets: XueyingJia/online_dpo_repo_augmented
library_name: transformers
model_name: pythia-160m-online-dpo-ground-truth-lead
tags:
- generated_from_trainer
- trl
- online-dpo
licence: license
---

# Model Card for pythia-160m-online-dpo-ground-truth-lead

This model is a fine-tuned version of [Audreygyj/pythia-160m-sft-HH-2-merge](https://huggingface.co/Audreygyj/pythia-160m-sft-HH-2-merge) on the [XueyingJia/online_dpo_repo_augmented](https://huggingface.co/datasets/XueyingJia/online_dpo_repo_augmented) 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="XueyingJia/pythia-160m-online-dpo-ground-truth-lead", 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/yujiagao-carnegie-mellon-university/huggingface/runs/flumvv3m)

This model was trained with Online DPO, a method introduced in [Direct Language Model Alignment from Online AI Feedback](https://huggingface.co/papers/2402.04792).

### Framework versions

- TRL: 0.13.0.dev0
- Transformers: 4.46.3
- Pytorch: 2.5.1
- Datasets: 3.1.0
- Tokenizers: 0.20.3

## Citations

Cite Online DPO as:

```bibtex
@article{guo2024direct,
    title        = {{Direct Language Model Alignment from Online AI Feedback}},
    author       = {Shangmin Guo and Biao Zhang and Tianlin Liu and Tianqi Liu and Misha Khalman and Felipe Llinares and Alexandre Ram{'{e}} and Thomas Mesnard and Yao Zhao and Bilal Piot and Johan Ferret and Mathieu Blondel},
    year         = 2024,
    eprint       = {arXiv:2402.04792}
}
```

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}}
}
```