Pinned Loading

1. GLM GLM Public

   GLM (General Language Model)

   Python 3.4k 333

2. slime slime Public

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

   Python 2.8k 317

3. P-tuning-v2 P-tuning-v2 Public

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

   Python 2.1k 205

4. ReST-MCTS ReST-MCTS Public

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

   Python 680 50

5. T1 T1 Public

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

   112 1

6. AgentRL AgentRL Public

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

   Python 141 8