Skip to content
ml-recall

#qlora

5 questions from Fine-tuning & PEFT

Timed test

5 questions · 5 min · score and explanations at the end

Take a test
Q 1 / 5Score 0 / 0

Question 1: Short answer

easyAI-checkedFine-tuning & PEFT

A model has 7 billion parameters. In bfloat16 its weights take 7×109×27 \times 10^9 \times 2 bytes =14= 14 GB. You load it with 4-bit quantization (load_in_4bit=True). Ignoring the small overhead of quantization constants, how many GB do the weights take now?

a number of GB (1 GB = 10^9 bytes)