Model Card for alpaca_supervised_kd_sft_Qwen2.5-3B-Instruct_from_Qwen2.5-7B-Instruct

This model is a fine-tuned version of Qwen/Qwen2.5-3B-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="distillslm/alpaca_supervised_kd_sft_Qwen2.5-3B-Instruct_from_Qwen2.5-7B-Instruct", 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 GKD, a method introduced in On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes.

Framework versions

• TRL: 0.15.2
• Transformers: 4.48.2
• Pytorch: 2.6.0
• Datasets: 3.2.0
• Tokenizers: 0.21.0

Citations

Cite GKD as:

@inproceedings{agarwal2024on-policy,
    title        = {{On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes}},
    author       = {Rishabh Agarwal and Nino Vieillard and Yongchao Zhou and Piotr Stanczyk and Sabela Ramos Garea and Matthieu Geist and Olivier Bachem},
    year         = 2024,
    booktitle    = {The Twelfth International Conference on Learning Representations, {ICLR} 2024, Vienna, Austria, May 7-11, 2024},
    publisher    = {OpenReview.net},
    url          = {https://openreview.net/forum?id=3zKtaqxLhW},
}

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}}
}