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
Commits on main
Repair four checks that went red on main with the decision-model merges (#12954)
d801c84 Daniel Han committed 1 month ago
Merge branch 'main' of https://github.com/unslothai/unsloth
0392472 Daniel Han committed 1 month ago
Studio: open Try a decision with the trained model after Use in Decision API (#12953)
9d32420 Nilay committed 1 month ago
Merge branch 'main' of https://github.com/unslothai/unsloth
69914a4 Daniel Han committed 1 month ago
Studio: price the context meter off a tool loop's final pass, not the whole turn's completions (#12889)
06bbb7f SlippyChimpMG committed 1 month ago
Studio: keep $PATH, $HOME and other shell variables as text, not maths (#12911)
a54bf4f Nilay committed 1 month ago
Studio: load ComfyUI nvfp4 and mxfp8 DiT single files (#12877)
2402838 Daniel Han committed 1 month ago
Studio: load ComfyUI text encoder and VAE files beside a single-file DiT (#12883)
8e259fd Daniel Han committed 1 month ago
Studio: load ComfyUI Krea-2 and HunyuanImage-2.1 single-file DiTs (#12885)
d1a3862 Daniel Han committed 1 month ago
Studio: load a single .safetensors DiT from any Hugging Face repo (#12879)
ebb079b Daniel Han committed 1 month ago
Studio: load Wan2.2 hosted FP8 / INT8 files, and hosted files under low_vram (#12888)
252fd53 Daniel Han committed 1 month ago
install-kernels: install mamba_ssm on sm75 with Triton 3.4+ (#12944)
e00ca87 Daniel Han committed 1 month ago
Settings contract: read the embedding picker's stacking classes inside cn() too (#12945)
26c86cb Daniel Han committed 1 month ago
Studio: update the audio.cpp runtime from the in-app update (#12893)
fed9f4d Etherl committed 1 month ago
Studio: show the hosted text encoder download in image load progress (#12894)
a5bf34b Etherl committed 1 month ago
Studio: fix live monitor background in light mode (#12904)
4162c85 Maheswar Kumar committed 1 month ago
Serve decision models through llama.cpp in Studio, and export them to GGUF (#12939)
15f715a Daniel Han committed 1 month ago
Studio: finish an update with the setup script it installed (#12897)
c0baa42 Etherl committed 1 month ago
Studio: read replies aloud without markdown symbols (#12598)
f21633e Aziz Muminov committed 1 month ago
Correct sample packing for hybrid models (gated-delta, Mamba2, short conv) (#9812)
7320e09 kfastino committed 1 month ago
Studio: install transformers releases needing hub >= 1.31, and transformers main after consent (#12871)
2cda887 Daniel Han committed 1 month ago
Train any text or vision LLM as a Clef decision model from Studio, with FastDecisionModel.predict and adapter saves (#12876)
4451666 Daniel Han committed 1 month ago
Train a decision model from a plain language model (#12772)
6cbf311 Daniel Han committed 1 month ago
Studio: load Wan2.2-A14B expert pairs and tell LTX-2.3 distilled from dev by its weights (#12872)
35f30b1 Daniel Han committed 1 month ago
Keep flash attention from reading Qwen3.5 mRoPE position ids as packed sequences (#12856)
c6cfbb7 Daniel Han committed 1 month ago
fix(studio): honor llama.cpp update dismissal and snooze (#12934)
b155de5 Wasim Yousef Said committed 1 month ago