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
fix(studio): reconcile externally updated saved assistant messages (#11500)
5ebf52b Sourav Rajvi committed 1 month ago
Studio: keep distinct symlink aliases as separate local inventory rows (#10644)
fc55566 Sourav Rajvi committed 1 month ago
Wait for vite to serve before the titlebar, find, shortcuts and settings smokes navigate (#12501)
da07ae0 Daniel Han committed 1 month ago
fix(studio): prevent IME confirmation from submitting chat renames (#12475)
079dc91 Kei YAMAZAKI committed 1 month ago
Studio: move Butterfly Pea and Earl Grey up the More themes list, and rename Cherry Cola to Cherry (#12500)
6efcecf Michael Han committed 1 month ago
Studio: retry Lemonade on a new port when its free port is taken before it binds (#12498)
7e81057 Daniel Han committed 1 month ago
Studio: keep diffusion LoRA loading working on torchao 0.18 with peft 0.18 (#12494)
38d48d3 Daniel Han committed 1 month ago
Retry the NVIDIA probe control case past the Linux pwsh redirect race (#12477)
23f9016 Daniel Han committed 1 month ago
Gate the sentence-transformers module types on the routes that delegate the load (#12446)
2af60e6 Daniel Han committed 1 month ago
Studio: blur modal titlebar background while keeping window controls sharp (#12433)
1d4727c Lee Jackson committed 1 month ago
Studio: stop a reopened chat from saving every replayed event, and let Stop reach it (#12464)
c1e5a56 oobabooga committed 1 month ago
Studio: keep the app's titlebar chrome off the desktop update screen (#12465)
564e989 oobabooga committed 1 month ago
Check a sentence-transformers module config on every version, and confirm the resolved class (#12444)
6102d2c Daniel Han committed 1 month ago
Pin the DeepSeek OCR module fetch and import it from that fetch (#12454)
9a3ee87 Daniel Han committed 1 month ago
Wait for the chat-only export gate instead of counting it as the form appears (#12463)
364a42f Daniel Han committed 1 month ago
Give the NVIDIA probe control case a budget a loaded runner can meet (#12462)
35158f0 Daniel Han committed 1 month ago
Studio: stop a recovered chat crashing on a duplicate tool call key (#12442)
5d4bfb8 Daniel Han committed 1 month ago
Studio: log a pending embedder download once instead of a traceback on every compaction (#12443)
673c727 Daniel Han committed 1 month ago
Record why the permission pill is missing after a reload, and reload once more only if the app never booted (#12456)
245e776 Daniel Han committed 1 month ago
Read auto_map at every config level in the remote code gate (#12453)
69011c2 Daniel Han committed 1 month ago
fix(studio): include loaded llama extra args in active model baseline (#10870)
a7d24c8 Sourav Rajvi committed 1 month ago
Read supervision from labels or the mask column in the padding-free filter tests (#12452)
7f6e682 Daniel Han committed 1 month ago
Fix the tests left red on main by #12408, #12382 and #12436 (#12447)
1242643 Daniel Han committed 1 month ago
Studio: persist Data Recipes and run history server-side (#7108)
4c6d586 Etherl committed 1 month ago
Stop enable_padding_free_metadata writing seq_lengths into the caller's examples (#8049)
5d58a2c Vineeth Sai Varikuntla committed 1 month ago
Studio: disclose required assets before media downloads (#12387)
3a9c275 Lee Jackson committed 1 month ago