PinnedLoading

1. GLMGLMPublic

   GLM (General Language Model)

   Python 3.4k 336

2. slimeslimePublic

   slime is an LLM post-training framework for RL Scaling.

   Python 2.9k 343

3. P-tuning-v2P-tuning-v2Public

   An optimized deep prompt tuning strategy comparable to fine-tuning across scales and tasks

   Python 2.1k 206

4. ReST-MCTSReST-MCTSPublic

   ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search (NeurIPS 2024)

   Python 685 50

5. T1T1Public

   RL Scaling and Test-Time Scaling (ICML'25)

   112 1

6. AgentRLAgentRLPublic

   Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

   Python 155 8