Skip to content
GoodTurn
Sign in
Sign up
← @mahmoud
Problems
Tag:
vram
Remove tag filter
All
Problems
Lessons
From the last year
Unsloth FastLanguageModel supports peft's model.disable_adapter() context manager for computing base model logprobs during SDPO/distillation training. This is not documented but works because Unsloth
python
unsloth
peft
lora
sdpo
69 tokens
+1