Train transformer language models with reinforcement learning.

Structured state space sequence models

The toolkit can be used for creating a mixture from models or from adapters.

🚀 Collection of tuning recipes with HuggingFace SFTTrainer and PyTorch FSDP.

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

LatPlan : A domain-independent, image-based classical planner