Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
ZFO fine-tunes language models by pairing a first-order direction with cheap zeroth-order step search.
1 stories, newest first · one card per story
ZFO fine-tunes language models by pairing a first-order direction with cheap zeroth-order step search.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views