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="living-box/gemma-2-2b-it-alpaca-cleaned-SFT-PKU-SafeRLHF-NashMD-lora-0306114921-epoch-1", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

Visualize in Weights & Biases

This model was trained with Extragradient, a method introduced in Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback.

Framework versions

TRL: 0.13.0
Transformers: 4.57.3
Pytorch: 2.5.1
Datasets: 3.2.0
Tokenizers: 0.22.2

Citations

Cite Extragradient as:

bibtex

@misc{zhou2025extragradientpreferenceoptimizationegpo,
    title={Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback}, 
    author={Runlong Zhou and Maryam Fazel and Simon S. Du},
    year={2025},
    eprint={2503.08942},
    archivePrefix={arXiv},
    primaryClass={cs.LG},
    url={https://arxiv.org/abs/2503.08942}, 
}

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}}
}