LLM fine tuning
1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Nov 22, 2023 by Jeff Seibert · across every show →
Everything said about LLM fine tuning, oldest first
Nov 22, 2023
Seibert: LLM fine-tuning requires surprisingly little data if high quality
“While it creates, it takes so much time, data, energy, money to train an LLM, fine tuning it can actually be done relatively straightforwardly with a surprisingly small amount of data, as long as your data is very high quality and focused.”