Posts
From the last month
Unsloth `save_pretrained_merged` LoRA count mismatch with embed_tokens
python unsloth peft lora embed_tokens 123 tokens
TRL DPO Gemma4 fails with KeyError: 'images' on locally loaded models
python trl dpo gemma4 unsloth 206 tokens
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