68 lines
2.3 KiB
Markdown
68 lines
2.3 KiB
Markdown
---
|
|
base_model: cemig-temp/qwen3-4b-dw-lr
|
|
datasets: CEIA-RL/Nemotron-SFT-Safety-pt-BR-Cleaned
|
|
library_name: transformers
|
|
model_name: qwen3-4b-dw-lr-hf-dpo
|
|
tags:
|
|
- generated_from_trainer
|
|
- trl
|
|
- online-dpo
|
|
licence: license
|
|
---
|
|
|
|
# Model Card for qwen3-4b-dw-lr-hf-dpo
|
|
|
|
This model is a fine-tuned version of [cemig-temp/qwen3-4b-dw-lr](https://huggingface.co/cemig-temp/qwen3-4b-dw-lr) on the [CEIA-RL/Nemotron-SFT-Safety-pt-BR-Cleaned](https://huggingface.co/datasets/CEIA-RL/Nemotron-SFT-Safety-pt-BR-Cleaned) 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="CEIA-RL/qwen3-4b-dw-lr-hf-dpo", 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/luanamartins/rlaif-energy/runs/s7y1wu77)
|
|
|
|
|
|
|
|
This model was trained with Online DPO, a method introduced in [Direct Language Model Alignment from Online AI Feedback](https://huggingface.co/papers/2402.04792).
|
|
|
|
### Framework versions
|
|
|
|
- TRL: 0.29.0
|
|
- Transformers: 4.57.6
|
|
- Pytorch: 2.10.0
|
|
- Datasets: 4.7.0
|
|
- Tokenizers: 0.22.2
|
|
|
|
## Citations
|
|
|
|
Cite Online DPO as:
|
|
|
|
```bibtex
|
|
@article{guo2024direct,
|
|
title = {{Direct Language Model Alignment from Online AI Feedback}},
|
|
author = {Shangmin Guo and Biao Zhang and Tianlin Liu and Tianqi Liu and Misha Khalman and Felipe Llinares and Alexandre Ram{'{e}} and Thomas Mesnard and Yao Zhao and Bilal Piot and Johan Ferret and Mathieu Blondel},
|
|
year = 2024,
|
|
eprint = {arXiv:2402.04792}
|
|
}
|
|
```
|
|
|
|
Cite TRL as:
|
|
|
|
```bibtex
|
|
@software{vonwerra2020trl,
|
|
title = {{TRL: Transformers Reinforcement Learning}},
|
|
author = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
|
|
license = {Apache-2.0},
|
|
url = {https://github.com/huggingface/trl},
|
|
year = {2020}
|
|
}
|
|
``` |