---
datasets:
- Reza8848/MUFFIN_68k
language:
- en
license: mit
---

<img src="https://cdn-uploads.huggingface.co/production/uploads/6434a6e8ea46c009904c617e/J_4FHXmtM6TuRnN3aL06y.png" width="38" height="38">


This is the model weight of **MUFFIN-T5-11B** (**Mu**lti-**F**aceted **In**structions).

We fine-tune the [T5-11B](https://huggingface.co/t5-11b) model on our [MUFFIN dataset](https://arxiv.org/abs/2312.02436).

We released both 3B and 11B models:
|Model|Number of parameters|
|-|-|
|[MUFFIN-T5-3B](https://huggingface.co/Reza8848/MUFFIN-T5-3B)|3 billion|
|[MUFFIN-T5-11B](https://huggingface.co/Reza8848/MUFFIN-T5-11B)|11 billion|

Please refer to [MUFFIN-T5-3B](https://huggingface.co/Reza8848/MUFFIN-T5-3B) for detailed documentation.




## 🥳 Citation

Please kindly cite our paper if you use any resources in this repository:

```bibtex
@inproceedings{Lou2023MUFFIN,
   title={{MUFFIN}: Curating Multi-Faceted Instructions for Improving Instruction Following},
   author={Renze Lou and Kai Zhang and Jian Xie and Yuxuan Sun and Janice Ahn and Hanzi Xu and Yu su and Wenpeng Yin},
   booktitle={The Twelfth International Conference on Learning Representations},
   year={2024},
   url={https://openreview.net/forum?id=1vrS1zwekw}
}
```