Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,15 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
## How to cite
|
| 2 |
|
| 3 |
If you find our work helpful, please feel free to cite the paper.
|
| 4 |
|
| 5 |
-
```
|
| 6 |
@article{nakamura2025optimalsparsitymixtureofexpertslanguage,
|
| 7 |
-
title={Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks},
|
| 8 |
author={Taishi Nakamura and Satoki Ishikawa and Masaki Kawamura and Takumi Okamoto and Daisuke Nohara and Jun Suzuki and Rio Yokota},
|
| 9 |
year={2025},
|
| 10 |
eprint={2508.18672},
|
| 11 |
archivePrefix={arXiv},
|
| 12 |
primaryClass={cs.LG},
|
| 13 |
-
url={https://arxiv.org/abs/2508.18672},
|
| 14 |
}
|
| 15 |
```
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: text-generation
|
| 3 |
+
library_name: transformers
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
tags:
|
| 6 |
+
- mixtral
|
| 7 |
+
- moe
|
| 8 |
+
- reasoning
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks
|
| 12 |
+
|
| 13 |
+
This repository contains model checkpoints from the paper [Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks](https://huggingface.co/papers/2508.18672).
|
| 14 |
+
|
| 15 |
+
For more details, including code and evaluation procedures, please refer to the official GitHub repository: [https://github.com/rioyokotalab/optimal-sparsity](https://github.com/rioyokotalab/optimal-sparsity)
|
| 16 |
+
|
| 17 |
## How to cite
|
| 18 |
|
| 19 |
If you find our work helpful, please feel free to cite the paper.
|
| 20 |
|
| 21 |
+
```bibtex
|
| 22 |
@article{nakamura2025optimalsparsitymixtureofexpertslanguage,
|
| 23 |
+
title={Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks},
|
| 24 |
author={Taishi Nakamura and Satoki Ishikawa and Masaki Kawamura and Takumi Okamoto and Daisuke Nohara and Jun Suzuki and Rio Yokota},
|
| 25 |
year={2025},
|
| 26 |
eprint={2508.18672},
|
| 27 |
archivePrefix={arXiv},
|
| 28 |
primaryClass={cs.LG},
|
| 29 |
+
url={https://arxiv.org/abs/2508.18672},
|
| 30 |
}
|
| 31 |
```
|
| 32 |
+
|