This model is a fine-tuned version of
Qwen/Qwen2-0.5B-Instruct.
It has been trained using
TRL.
1from transformers import pipeline
2
3question = "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?"
4generator = pipeline("text-generation", model="qgallouedec/Qwen2-0.5B-OnlineDPO", device="cuda")
5output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
6print(output["generated_text"])
This model was trained with Online DPO, a method introduced in
Direct Language Model Alignment from Online AI Feedback.
1@article{guo2024direct,
2 title = {{Direct Language Model Alignment from Online AI Feedback}},
3 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},
4 year = 2024,
5 eprint = {arXiv:2402.04792}
6}
1@misc{vonwerra2022trl,
2 title = {{TRL: Transformer Reinforcement Learning}},
3 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},
4 year = 2020,
5 journal = {GitHub repository},
6 publisher = {GitHub},
7 howpublished = {\url{https://github.com/huggingface/trl}}
8}
