Popular repositories Loading

1. self-refinement self-refinement Public

   Python

2. efficient_llm_experiments efficient_llm_experiments Public

   Efficient LLM Experiments: TTT-LoRA, KV-Cache Compression, Speculative Decoding, Mixed-Precision Quantization, Full Stack Optimization

   Python

3. adaptive-prm-simulator adaptive-prm-simulator Public

   Adaptive Process Reward Model with Generative Difficulty Scaling for LLM Agent Training

   Python

4. agentforge agentforge Public

   Python

5. prime-rl prime-rl Public

   Forked from PrimeIntellect-ai/prime-rl

   Async RL Training at Scale

   Python

6. philo-benchmark philo-benchmark Public

   Automated evaluation pipeline for physics reasoning plausibility in video generation models (Kling 1.6 vs Veo 3)

   Python