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="QpiEImitation/OPD-expectation-tr-S-Qwen3.5-4B_T-Qwen3.5-9B", 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 GKD, a method introduced in On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes.

Framework versions

TRL: 1.0.0.dev0
Transformers: 5.12.1
Pytorch: 2.12.1
Datasets: 3.0.0
Tokenizers: 0.22.2

Citations

Cite GKD as:

bibtex

@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:

bibtex

@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}
}