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.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
Update pyproject.toml
Daniel Han51fb0844b733
diff --git a/pyproject.toml b/pyproject.tomlindex f982b6db147..2aa193a6b3d 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -235,7 +235,7 @@ huggingfacenotorch = [## 2026.9.9 is the first zoo carrying the ceilings below and the Gemma3 token_type_ids fix# (unsloth-zoo#1505) that transformers >= 5.15 needs.- "unsloth_zoo>=2026.10.7",+ "unsloth_zoo>=2026.10.8","wheel>=0.42.0","packaging","numpy",@@ -303,7 +303,7 @@ audio-torch280 = []huggingface = ["unsloth[huggingfacenotorch]",- "unsloth_zoo>=2026.10.7",+ "unsloth_zoo>=2026.10.8","torchvision","unsloth[triton]",]@@ -975,7 +975,7 @@ colab-ampere-torch220 = ["flash-attn>=2.6.3 ; ('linux' in sys_platform)",]colab-new = [- "unsloth_zoo>=2026.10.7",+ "unsloth_zoo>=2026.10.8","packaging","tyro","transformers>=4.52.4,!=4.53.0,!=4.54.0,!=4.55.0,!=4.55.1,!=4.57.0,!=4.57.4,!=4.57.5,!=5.0.0,!=5.1.0,<=5.17.0",