--- library_name: transformers model_name: Qwen3-VL-2B-2 tags: - generated_from_trainer - grpo - hf_jobs - trl licence: license --- # Model Card for Qwen3-VL-2B-2 This model is a fine-tuned version of [None](https://huggingface.co/None). It has been trained using [TRL](https://github.com/huggingface/trl). ## Quick start ```python 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="Paradoxis/Qwen3-VL-2B-2", 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](https://wandb.ai/flofiz-universit-de-bourgogne/GRPO_HTML/runs/j6kf4yvu) This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300). ### Framework versions - TRL: 0.23.1 - Transformers: 5.0.0.dev0 - Pytorch: 2.8.0+cu126 - Datasets: 4.2.0 - Tokenizers: 0.22.1 ## Citations Cite GRPO as: ```bibtex @article{shao2024deepseekmath, title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}}, author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo}, year = 2024, eprint = {arXiv:2402.03300}, } ``` Cite TRL as: ```bibtex @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}} } ```