Roland Tannous 0050e78aa3 Fix in-memory transformers version detection and aggressive module purge for 5.1.0/4.57.1 switching		2026-02-22 19:08:18 +00:00
..
assets	fix: correct vision LoRA defaults for VLMs and remove vision fields from text-only model configs	2026-02-22 15:09:10 +00:00
auth	fix: rollback auth.db user row if token generation fails during setup	2026-02-13 10:11:07 +00:00
core	fix: pass full Processor as processing_class for VLM SFTTrainer	2026-02-22 14:11:12 +00:00
loggers	root studio folder	2026-02-02 09:13:49 +00:00
models	feat: add schemas for local model discovery and listing	2026-02-17 21:53:42 +01:00
requirements	add huggingface-hub==0.36.0 due to colab error	2026-02-20 18:26:20 +00:00
routes	Auto-switch transformers version (5.1.0/4.57.1) for Ministral-3, GLM-4.7-Flash, Qwen3-30B-A3B models with LoRA adapter resolution	2026-02-22 18:29:40 +00:00
state	root studio folder	2026-02-02 09:13:49 +00:00
tests	added @needs_torch to test_cuda_oom	2026-02-11 16:12:37 +00:00
utils	Fix in-memory transformers version detection and aggressive module purge for 5.1.0/4.57.1 switching	2026-02-22 19:08:18 +00:00
colab.py	feat: Add simple 2-cell Colab notebook (no tunnel needed)	2026-02-17 04:57:30 -06:00
main.py	renamed UNSLOTH_FLEX_ATTENTION to UNSLOTH_ENABLE_FLEX_ATTENTION	2026-02-18 09:21:53 +00:00
run.py	fix path in run_server	2026-02-14 05:06:17 +00:00