LoRA and QLoRA fine-tuning configs
LoRA and QLoRA configs to retrain a model on a budget, with Axolotl or Unsloth.
Nobody has published here yet. Why not you?
What is a LoRA config?
LoRA adapts an existing model to a task without fully retraining it: only small adapters are trained. A LoRA page gathers all the settings of that training.
Guide: LoRA →