Train transformer language models with reinforcement learning.

Fully open reproduction of DeepSeek-R1

Our library for RL environments + evals

LLM Router is an open-source project for building, training, and running a transformer-based router that picks the best LLM for each query. It helps balance cost and quality of the responses. The r…

Lectura is a streamlined tool that automatically generates comprehensive, well-structured notes from lecture recordings and slides using AI models. It supports both local and cloud-based AI providers.