1dff1a7 1ee68bf b1d78ad
1
2
3
4
5
6
7
8
9
10
11
12
13
--- title: README emoji: 👀 colorFrom: gray colorTo: indigo sdk: static pinned: false --- 🐙 OctoThinker is led by [GAIR](https://huggingface.co/GAIR) 🎯 Our Goal: To reshape the pre-training trajectory so models scale better under RL.
