PrototypeCommon
GAIR-NLP/OctoThinker
Revisiting Mid-training in the Era of Reinforcement Learning Scaling
- Owner
- GAIR-NLP (organization)
- Stars
- Stars: 188
- Forks
- Forks: 15
- Language
- Jupyter Notebook
- License
- Apache-2.0
- Created
- 2025
- Topics
- llamallmpost-trainingpre-trainingqwenreasoningrlverlmid-training
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by GAIR-NLP
All 31 repos by GAIR-NLP- GAIR-NLP/daVinci-MagiHumanStars: 2,122PythonRC
- GAIR-NLP/O1-JourneyStars: 1,997Beta
- GAIR-NLP/ASI-ArchStars: 1,190PythonBeta
- GAIR-NLP/LIMOStars: 1,083PythonBeta
- GAIR-NLP/factoolStars: 935PythonBeta
- GAIR-NLP/ASI-EvolveStars: 872PythonBeta
Nearby in Jupyter Notebook
All Jupyter Notebook repos- ibm-granite/granite-guardianStars: 188Jupyter NotebookPrototype
- nickjiang2378/test-time-registersStars: 188Jupyter NotebookPrototype
- Square-Zero-Labs/Wan2GP-on-ColabStars: 188Jupyter NotebookPrototype
- mcleonard/blog_postsStars: 188Jupyter NotebookPrototype
- may-/cnn-re-tfStars: 188Jupyter NotebookPrototype
- davideverona/deep-crowd-counting_crowdnetStars: 188Jupyter NotebookPrototype