rloo-gsm8k

Model Card for output

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct. It has been trained using TRL.

Quick start

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="None", 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 RLOO, a method introduced in Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs.

Framework versions

• PEFT 0.19.1
• TRL: 1.7.1
• Transformers: 5.13.1
• Pytorch: 2.11.0+cu128
• Datasets: 5.0.1
• Tokenizers: 0.22.2

Citations

Cite RLOO as:

@inproceedings{ahmadian2024back,
    title        = {{Back to Basics: Revisiting REINFORCE-Style Optimization for Learning from Human Feedback in LLMs}},
    author       = {Arash Ahmadian and Chris Cremer and Matthias Gall{'{e}} and Marzieh Fadaee and Julia Kreutzer and Olivier Pietquin and Ahmet {"{U}}st{"{u}}n and Sara Hooker},
    year         = 2024,
    booktitle    = {Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), {ACL} 2024, Bangkok, Thailand, August 11-16, 2024},
    pages        = {12248--12267},
    publisher    = {Association for Computational Linguistics},
    editor       = {Lun{-}Wei Ku and Andre Martins and Vivek Srikumar},
}

Cite TRL as:

@software{vonwerra2020trl,
  title   = {{TRL: Transformers Reinforcement Learning}},
  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
  license = {Apache-2.0},
  url     = {https://github.com/huggingface/trl},
  year    = {2020}
}