Instruction Tuning
topic on 2 shows · 5 statements across 3 episodes
Latent Space 
A Product Market Fit Show
5 statements about Instruction Tuning, every show
Frosst: Fine-Tuned LLMs Generalize to Unseen Request Types
“If you train it on just those conversations, and you It's never been asked to do a summary. It will still be a, do a good job when you ask it to do a summary. So it generalizes to request is never asked, never been asked in the training data.”
Conover: The next generation of AI innovation requires specialized tuning data
“And I think the cost of producing instruction tuning and fine tuning data that creates specific kinds of behaviors, I think that's probably where the next generation of really interesting work starts to happen.”
Lambert: Instruction tuning is more important than RLHF for most practitioners
“I think for most people, instruction tuning is probably still more important in their day-to-day life. I think instruction tuning works very well. You can write samples by hand that make sense. You can get the model to learn from them. You could do this with v…”
Lambert: Scaling from 7B to 70B parameters fixes nuance and repetition
“I think the things that people see now is like the small models don't really handle nuance as well, and they could be more repetitive if, even if they have really good instruction tuning, but if you take that kind of seven to seventy billion parameter jump, li…”
Lambert: The vast majority of instruction tuning data remains simple Q&A
“There's much more, like there's surely kind of more tricky things that people do, but I still think the vast majority of it is question and answer. It's like, please explain this topic to me, generate this thing for me. That hasn't changed that much this year.…”