The Fine-Tuning Index / RLHF & Preference / #32
baidu-baige/LoongForge
by baidu-baige · RLHF & Preference · updated 4d ago
A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T-N1.7, FastWAM, Cosmos3, DreamZero, DeepSeek-V4, GLM-5.3, Kimi-K3 and more.
63
momentum
732
stars
63
forks
#32
rank
gpukunlunllmloramegatronmid-trainingpretrainingsfttorchvlavlmwam
View on GitHub →