Model Card for None
This model is a fine-tuned version of Qwen/Qwen2.5-7B-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 SFT.
Framework versions
- TRL: 0.12.0
- Transformers: 4.51.1
- Pytorch: 2.5.1+cu124
- 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 Gallouédec},
year = 2020,
journal = {GitHub repository},
publisher = {GitHub},
howpublished = {\url{https://github.com/huggingface/trl}}
}
Provenance (FAIR cluster backup, 2026-09-14)
- Source dir:
/checkpoint/comem/shannons/latent-cot/ckpts-w17/20250923-200848~gist~Qwen2.5-7B-Instruct~ot3-1.2m-10k-converted~bs128~lr4e-5~epoch5~l21000~gz3+d-sentence+cross_gist+input+wrap_gist_token+wrap_gist_token_to_special_tokens+use_latent_ema+iter2+weight0.2+mask-v2+keep_math_span - Launch:
train/commands/week17/09-23-gist-ot-10k-alpha-0.2-latent-v2-iter-2-qwen2.5-7b-sentence-3.sh - Base model:
Qwen/Qwen2.5-7B-Instruct· Dataset:shannons/ot3-1.2m-10k-converted - Paper row: Paper Table 1: Qwen2.5-7B LaTexT m=3 sentence