BodElseht/outputs

1---2library_name: transformers3model_name: outputs4tags:5- generated_from_trainer6- trl7- sft8licence: license9---10 11# Model Card for outputs12 13This model is a fine-tuned version of [None](https://huggingface.co/None).14It has been trained using [TRL](https://github.com/huggingface/trl).15 16## Quick start17 18```python19from transformers import pipeline20 21question = "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?"22generator = pipeline("text-generation", model="BodElseht/outputs", device="cuda")23output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]24print(output["generated_text"])25```26 27## Training procedure28 29[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/elsehtabdelrahman-mansoura-university/huggingface/runs/usdpu29g)30 31This model was trained with SFT.32 33### Framework versions34 35- TRL: 0.12.136- Transformers: 4.47.0.dev037- Pytorch: 2.5.1+cu12138- Datasets: 3.1.039- Tokenizers: 0.20.340 41## Citations42 43 44 45Cite TRL as:46    47```bibtex48@misc{vonwerra2022trl,49	title        = {{TRL: Transformer Reinforcement Learning}},50	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},51	year         = 2020,52	journal      = {GitHub repository},53	publisher    = {GitHub},54	howpublished = {\url{https://github.com/huggingface/trl}}55}56```