Tag: QLoRA
-
QLoRA Explained: A 4-Bit Base, NF4, and What It Really Costs
QLoRA puts a 7B to 30B fine-tune on one card. NF4, double quantisation, paged optimizers, the throughput tax nobody mentions, and the…
-
LLM Fine-Tuning Explained: What Actually Changes Inside the Model
LLM fine-tuning runs the pretraining objective on your data with a loss mask. What actually changes, when to do it, and how…