|
|
--- |
|
|
title: README |
|
|
emoji: 🐢 |
|
|
colorFrom: yellow |
|
|
colorTo: green |
|
|
sdk: static |
|
|
pinned: false |
|
|
--- |
|
|
|
|
|
# Resa: Transparent Reasoning Models via SAE |
|
|
|
|
|
**Resa** is the family of 1.5B models created via sparse autoencoder tuning (SAE-Tuning) on open-source reasoning datasets. |
|
|
|
|
|
* **Paper**: [https://arxiv.org/abs/2506.09967](https://arxiv.org/abs/2506.09967) |
|
|
* **Notion Blog**: [https://shangshangwang.notion.site/resa](https://shangshangwang.notion.site/resa) |
|
|
* **Code Repository**: [https://github.com/shangshang-wang/Resa](https://github.com/shangshang-wang/Resa) |
|
|
* **Training Logs**: [https://wandb.ai/upup-ashton-wang-usc/Resa](https://wandb.ai/upup-ashton-wang-usc/Resa) |
|
|
|
|
|
*Resa's avatar is generated by GPT-4o based on [KYNE](https://www.artsy.net/artist/kyne)'s girls and the following prompt.* |
|
|
|
|
|
*Hey hey! I’m Resa — total ENTJ energy here 💥 I *love* meeting new people (friends are everything!!), and I’m all about chasing good vibes through amazing food, spontaneous travel, artsy sketches, and singing my heart out wherever I go! 🎨✈️🍜🎤 ... Oops, almost forget, I am super into large language model reasoning, too!* |
|
|
|
