MengsD/Megatron-Bridge-slime
Training library for Megatron-based models
Repositories
MengsD/slime
slime is an LLM post-training framework for RL Scaling.
MengsD/Trinity-RFT
Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).
MengsD/agentscope
Start building LLM-empowered multi-agent applications in an easier way.
MengsD/OpenJudge
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
MengsD/past-dependencies
Dependent jars for PAST