RUCBM/LaSeR
Optimizes reasoning and self-rewarding capabilities of LLMs
View on index · View in 3D Map
Related repos
- Lifelong memory for LLM agents
- Agentic LLM for autonomous data science
- Process manager using LLMs to analyze and roast system activity
- Discovers tools for autonomous agents
- Builds knowledge through conversations with LLMs
- Collection of papers on LLM reasoning
- OpenAI-compatible proxy that boosts LLM reasoning accuracy with 20+ optimization techniques, no retraining needed
- Training LLMs with half the backward pass FLOPs
- Fine-tunes LLMs on Apple silicon
- Empowers reasoning models with deep research capabilities
