volcengine/verl

reinforcement learning library for training large language models, supports many RL algorithms, integrates with LLM tools, scales to models with up to 671B parameters

View on index

Related repos

• open-source reinforcement learning for language models
  agentica-project/rllm
• large language model tutorials and training basics from scratch
  datawhalechina/happy-llm
• Code and tutorials for building large language models from scratch in PyTorch
  rasbt/LLM-workshop-2024
• RNN meets transformer for efficient large language models
  BlinkDL/RWKV-LM
• minimal repo for language model policy optimization with RL
  kvfrans/lmpo
• run large language models on any device
  mlc-ai/mlc-llm
• open notes and guides for training large language models
  stas00/ml-engineering
• Course for learning about large language models using roadmaps and Colab notebooks
  mlabonne/llm-course
• Large language model using diffusion for text generation
  ML-GSAI/LLaDA
• Library for running and serving large language models
  vllm-project/vllm