https://github.com/agentica-project/deepscaler

Democratizing Reinforcement Learning for LLMs
https://github.com/agentica-project/deepscaler

Last synced: 4 months ago
JSON representation

Democratizing Reinforcement Learning for LLMs

• Host: GitHub
• URL: https://github.com/agentica-project/deepscaler
• Owner: agentica-project
• License: mit
• Created: 2025-01-26T05:31:40.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2025-02-10T22:32:18.000Z (4 months ago)
• Last Synced: 2025-02-10T23:26:36.562Z (4 months ago)
• Language: Python
• Homepage: https://www.agentica-project.com
• Size: 11.5 MB
• Stars: 16
• Watchers: 1
• Forks: 1
• Open Issues: 0

Awesome Lists containing this project

• awesome-rl-reasoning-recipes - deepscaler
• awesome-rl-reasoning-recipes - deepscaler
• awesome-llm-and-aigc - DeepScaleR - project/deepscaler?style=social"/> : Democratizing Reinforcement Learning for LLMs. [www.agentica-project.com](https://www.agentica-project.com/). ["DeepScaleR: Surpassing O1-Preview with a 1.5B Model by Scaling RL"](https://pretty-radio-b75.notion.site/DeepScaleR-Surpassing-O1-Preview-with-a-1-5B-Model-by-Scaling-RL-19681902c1468005bed8ca303013a4e2) (Summary)
• Awesome-Efficient-Reasoning-Models - DeepScaleR - project.com/) (Full list / Build SLM with Strong Reasoning Ability)
• Awesome-Efficient-Reasoning-Models - DeepScaleR - project.com/) (Full list / Build SLM with Strong Reasoning Ability)
• StarryDivineSky - agentica-project/deepscaler