unsloth/studio/backend
Roland Tannous 706eaeae36 fix: use max_completion_tokens for OpenAI provider
Newer OpenAI models (gpt-4o, gpt-5.x) reject the max_tokens param
and require max_completion_tokens instead. Other providers still use
max_tokens.
2026-04-08 11:16:44 +04:00
..
assets fix(studio): correct default weight_decay and learning rate (#4695) 2026-03-31 13:50:25 +04:00
auth fix: remove old comments (#4292) 2026-03-14 16:50:13 +04:00
core fix: use max_completion_tokens for OpenAI provider 2026-04-08 11:16:44 +04:00
loggers Final cleanup 2026-03-12 18:28:04 +00:00
models Studio: API external provider registry + curated catalogs (HF/OpenRouter) and chat UX (#4787) 2026-04-04 10:28:15 +04:00
plugins Bump Data Designer to 0.5.4 (removes litellm dependency) (#4569) 2026-03-25 02:01:43 -07:00
requirements Merge branch 'main' into feature/chat-api 2026-04-01 18:28:44 +00:00
routes Studio: API external provider registry + curated catalogs (HF/OpenRouter) and chat UX (#4787) 2026-04-04 10:28:15 +04:00
state Final cleanup 2026-03-12 18:28:04 +00:00
storage Merge branch 'main' into feature/chat-api 2026-04-01 18:28:44 +00:00
tests Studio: API external provider registry + curated catalogs (HF/OpenRouter) and chat UX (#4787) 2026-04-04 10:28:15 +04:00
utils Fix Windows local GGUF model loading crash (#4730) 2026-04-01 01:38:09 -07:00
__init__.py Final cleanup 2026-03-12 18:28:04 +00:00
_platform_compat.py Fix Studio crash on Anaconda/conda-forge Python (#4484) 2026-03-22 05:36:55 -07:00
colab.py Allow install_python_stack to run on Colab (#4633) 2026-03-27 00:29:27 +04:00
main.py Merge branch 'main' into feature/chat-api 2026-04-01 18:28:44 +00:00
run.py fix(studio): avoid UnicodeEncodeError on Windows cp1252 consoles (#4699) 2026-03-30 06:40:47 -07:00
startup_banner.py studio: unify Windows installer/setup logging style, verbosity controls, and startup messaging (#4651) 2026-03-30 00:53:23 -07:00