| | --- |
| | base_model: unsloth/mistral-7b-v0.3-bnb-4bit |
| | library_name: transformers |
| | model_name: kto_simplification_imbalanced |
| | tags: |
| | - generated_from_trainer |
| | - unsloth |
| | - kto |
| | - trl |
| | licence: license |
| | --- |
| | |
| | # Model Card for kto_simplification_imbalanced |
| |
|
| | This model is a fine-tuned version of [unsloth/mistral-7b-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit). |
| | 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="IoakeimE/kto_simplification_imbalanced", device="cuda") |
| | output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0] |
| | print(output["generated_text"]) |
| | ``` |
| |
|
| | ## Training procedure |
| |
|
| | [<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/ioakeime-aristotle-university-of-thessaloniki/kto_smiplification_imbalanced/runs/po8ovzhv) |
| |
|
| |
|
| | This model was trained with KTO, a method introduced in [KTO: Model Alignment as Prospect Theoretic Optimization](https://huggingface.co/papers/2402.01306). |
| |
|
| | ### Framework versions |
| |
|
| | - TRL: 0.19.0 |
| | - Transformers: 4.53.0 |
| | - Pytorch: 2.7.0+cu128 |
| | - Datasets: 3.6.0 |
| | - Tokenizers: 0.21.2 |
| |
|
| | ## Citations |
| |
|
| | Cite KTO as: |
| |
|
| | ```bibtex |
| | @article{ethayarajh2024kto, |
| | title = {{KTO: Model Alignment as Prospect Theoretic Optimization}}, |
| | author = {Kawin Ethayarajh and Winnie Xu and Niklas Muennighoff and Dan Jurafsky and Douwe Kiela}, |
| | year = 2024, |
| | eprint = {arXiv:2402.01306}, |
| | } |
| | ``` |
| |
|
| | 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}} |
| | } |
| | ``` |
