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 Handf5b23150e37
diff --git a/pyproject.toml b/pyproject.tomlindex e4d299e9794..ae8f3b9c4f1 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -218,7 +218,7 @@ huggingfacenotorch = [# `transformers<=5.5.0` in its own metadata, so the resolver intersects our transformers# range down to 5.5.0 whatever this file says. That one waits on# unslothai/unsloth-zoo#1227 and a later zoo release.- "unsloth_zoo>=2026.9.5",+ "unsloth_zoo>=2026.9.6","wheel>=0.42.0","packaging","numpy",@@ -284,7 +284,7 @@ audio-torch280 = []huggingface = ["unsloth[huggingfacenotorch]",- "unsloth_zoo>=2026.9.5",+ "unsloth_zoo>=2026.9.6","torchvision","unsloth[triton]",]@@ -903,7 +903,7 @@ colab-ampere-torch220 = ["flash-attn>=2.6.3 ; ('linux' in sys_platform)",]colab-new = [- "unsloth_zoo>=2026.9.5",+ "unsloth_zoo>=2026.9.6","packaging","tyro","transformers>=4.51.3,!=4.52.0,!=4.52.1,!=4.52.2,!=4.52.3,!=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,<=5.5.0",