# GAIR-NLP/OctoThinker

<https://repo.masters-masters.com/en/repos/GAIR-NLP/OctoThinker>

[Home](https://repo.masters-masters.com/en) › [GAIR-NLP](https://repo.masters-masters.com/en/owners/GAIR-NLP) › [OctoThinker](https://repo.masters-masters.com/en/repos/GAIR-NLP/OctoThinker)

GAIR-NLP/OctoThinker has 188 stars on GitHub. Its RepoMasters card: Prototype tier. Revisiting Mid-training in the Era of Reinforcement Learning Scaling

| Field | Value |
| --- | --- |
| Owner | [GAIR-NLP](https://repo.masters-masters.com/en/owners/GAIR-NLP) |
| Stars | 188 |
| Forks | 15 |
| Language | [Jupyter Notebook](https://repo.masters-masters.com/en/languages/jupyter-notebook) |
| License | Apache-2.0 |
| Created | 2025 |
| Topics | llama, llm, post-training, pre-training, qwen, reasoning, rl, verl, mid-training |
| Tier | [Prototype (100 to 249 ★)](https://repo.masters-masters.com/en/ranks/rush) |
| View on GitHub | [GAIR-NLP/OctoThinker](https://github.com/GAIR-NLP/OctoThinker) |

## Repository

Revisiting Mid-training in the Era of Reinforcement Learning Scaling

The tier for repos with 100 to 249 ★. Published odds per card pulled: 70%. Rarity: Common.

## More repos by GAIR-NLP

- [GAIR-NLP/daVinci-MagiHuman · ★ 2,122 · Python · RC](https://repo.masters-masters.com/en/repos/GAIR-NLP/daVinci-MagiHuman)
- [GAIR-NLP/O1-Journey · ★ 1,997 · Beta](https://repo.masters-masters.com/en/repos/GAIR-NLP/O1-Journey)
- [GAIR-NLP/ASI-Arch · ★ 1,190 · Python · Beta](https://repo.masters-masters.com/en/repos/GAIR-NLP/ASI-Arch)
- [GAIR-NLP/LIMO · ★ 1,083 · Python · Beta](https://repo.masters-masters.com/en/repos/GAIR-NLP/LIMO)
- [GAIR-NLP/factool · ★ 935 · Python · Beta](https://repo.masters-masters.com/en/repos/GAIR-NLP/factool)
- [GAIR-NLP/ASI-Evolve · ★ 872 · Python · Beta](https://repo.masters-masters.com/en/repos/GAIR-NLP/ASI-Evolve)

## Nearby in Jupyter Notebook

- [yu-rp/KANbeFair · ★ 188 · Jupyter Notebook · Prototype](https://repo.masters-masters.com/en/repos/yu-rp/KANbeFair)
- [nickjiang2378/test-time-registers · ★ 188 · Jupyter Notebook · Prototype](https://repo.masters-masters.com/en/repos/nickjiang2378/test-time-registers)
- [Square-Zero-Labs/Wan2GP-on-Colab · ★ 188 · Jupyter Notebook · Prototype](https://repo.masters-masters.com/en/repos/Square-Zero-Labs/Wan2GP-on-Colab)
- [mcleonard/blog\_posts · ★ 188 · Jupyter Notebook · Prototype](https://repo.masters-masters.com/en/repos/mcleonard/blog_posts)
- [may-/cnn-re-tf · ★ 188 · Jupyter Notebook · Prototype](https://repo.masters-masters.com/en/repos/may-/cnn-re-tf)
- [davideverona/deep-crowd-counting\_crowdnet · ★ 188 · Jupyter Notebook · Prototype](https://repo.masters-masters.com/en/repos/davideverona/deep-crowd-counting_crowdnet)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.