|
|
--- |
|
|
base_model: Qwen/Qwen3-4B |
|
|
datasets: trl-lib/Capybara |
|
|
library_name: transformers |
|
|
model_name: Qwen3-4B-SFT |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
- trl |
|
|
- sft |
|
|
licence: license |
|
|
--- |
|
|
|
|
|
# Model Card for Qwen3-4B-SFT |
|
|
|
|
|
This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B) on the [trl-lib/Capybara](https://huggingface.co/datasets/trl-lib/Capybara) 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="sergiopaniego/Qwen3-4B-SFT", 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: 0.23.1 |
|
|
- Transformers: 4.56.2 |
|
|
- Pytorch: 2.8.0+cu126 |
|
|
- Datasets: 4.0.0 |
|
|
- Tokenizers: 0.22.1 |
|
|
|
|
|
## 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 Gallou{\'e}dec}, |
|
|
year = 2020, |
|
|
journal = {GitHub repository}, |
|
|
publisher = {GitHub}, |
|
|
howpublished = {\url{https://github.com/huggingface/trl}} |
|
|
} |
|
|
``` |
