https://github.com/Gen-Verse/ReasonFlux

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates
https://github.com/Gen-Verse/ReasonFlux

chain-of-thought deepseek-r1 deepseek-v3 llm-rlhf o1-mini o1-preview reinforcement-learning sft-data

Last synced: about 1 month ago
JSON representation

ReasonFlux: Hierarchical LLM Reasoning via Scaling Thought Templates

• Host: GitHub
• URL: https://github.com/Gen-Verse/ReasonFlux
• Owner: Gen-Verse
• License: apache-2.0
• Created: 2025-02-10T11:04:39.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2025-03-22T01:00:05.000Z (about 1 month ago)
• Last Synced: 2025-03-22T01:18:58.700Z (about 1 month ago)
• Topics: chain-of-thought, deepseek-r1, deepseek-v3, llm-rlhf, o1-mini, o1-preview, reinforcement-learning, sft-data
• Language: Python
• Homepage: https://arxiv.org/abs/2502.06772
• Size: 12.4 MB
• Stars: 351
• Watchers: 5
• Forks: 27
• Open Issues: 6
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• StarryDivineSky - Gen-Verse/ReasonFlux