--- base_model: silx-ai/Quasar-3.3-Max datasets: eyad-silx/Qausar-3.7-coding library_name: transformers model_name: Quasar-3.7-Coding tags: - generated_from_trainer - open-r1 - trl - sft licence: license --- # Model Card for Quasar-3.7-Coding This model is a fine-tuned version of [silx-ai/Quasar-3.3-Max](https://huggingface.co/silx-ai/Quasar-3.3-Max) on the [eyad-silx/Qausar-3.7-coding](https://huggingface.co/datasets/eyad-silx/Qausar-3.7-coding) dataset. 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="silx-ai/Quasar-3.7-Coding", 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/mentoxcompuny-silx-ai/huggingface/runs/9y6ifu0f) This model was trained with SFT. ### Framework versions - TRL: 0.16.0.dev0 - Transformers: 4.49.0 - Pytorch: 2.5.1 - Datasets: 3.3.2 - Tokenizers: 0.21.0 ## Citations 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 Gallouédec}, year = 2020, journal = {GitHub repository}, publisher = {GitHub}, howpublished = {\url{https://github.com/huggingface/trl}} } ```