Popular repositories Loading

1. fast-start fast-start Public

   Быстро стартуем

   1 1

2. simpleRL-reason simpleRL-reason Public

   Forked from hkust-nlp/simpleRL-reason

   This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

   Python 1

3. RAGEN RAGEN Public

   Forked from ZihanWang314/RAGEN

   RAGEN is the first open-source reproduction of DeepSeek-R1 for training agentic models via reinforcement learning.

   Python 1

4. reasoning-gym-ru reasoning-gym-ru Public

   Forked from open-thought/reasoning-gym

   procedural reasoning datasets

   Python

5. state-of-ai state-of-ai Public

   Собираем и объясняем статьи

6. verl verl Public

   Forked from volcengine/verl

   veRL: Volcano Engine Reinforcement Learning for LLM

   Python