Model Card for Qwen2.5-0.5B-PRM-RAD-balanced-V4

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B. 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="alothomas/Qwen2.5-0.5B-PRM-RAD-balanced-V4", 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 PRM.

Framework versions

• TRL: 0.15.1
• Transformers: 4.49.0
• Pytorch: 2.6.0
• Datasets: 3.3.1
• Tokenizers: 0.21.0

Citations

Cite PRM as:

@article{uesato2022solving,
    title        = {{Solving Math Word Problems With Process- and Outcome-Based Feedback}},
    author       = {Uesato, Jonathan and Kushman, Nate and Kumar, Ramana and Song, Francis and Siegel, Noah and Wang, Lisa and Creswell, Antonia and Irving, Geoffrey and Higgins, Irina},
    year         = 2022,
    journal      = {arXiv preprint arXiv:2211.14275}
}

Cite TRL as:

@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}}
}