Skip to content

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.

Commits on main

GRPO: log the clip_ratio metrics for loss_type luspo (#17537)
Vineeth Sai Varikuntla committed 8 days ago
eb34918
push_to_hub_gguf: put the user's tags in the README card (#17438)
Vineeth Sai Varikuntla committed 8 days ago
e0ba54e
d26a6ce
61d752f
e25b5d1