Model Card for gpt2-sft

This model is a fine-tuned version of openai-community/gpt2. 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="gumran/gpt2-sft", 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 SFT.

Framework versions

• TRL: 0.18.1
• Transformers: 4.52.4
• Pytorch: 2.7.1+cu118
• Datasets: 3.6.0
• Tokenizers: 0.21.1

Citations

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 Gallou{\'e}dec},
 year = 2020,
 journal = {GitHub repository},
 publisher = {GitHub},
 howpublished = {\url{https://github.com/huggingface/trl}}
}

Base model

openai-community/gpt2

(2185)

Code: https://github.com/gumran/post-training • 3 items • Updated Jun 22, 2025