Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How to Finetune GPT-Like Large Language Models on a Custom Dataset

lightning.ai

Post reply on HN
Print view View original

91–100 of 126 posts

Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset

#91

Post by fnordpiglet »

tsunamifury wrote: post #88
fnordpiglet wrote: post #82

Earlier quoted context omitted.

This is true - afaik there’s been no specific rulings on whether training models on copyright material is a violation. But to my mind it harkens back to stuff like xerox and such where the tool itself isn’t the violating thing it’s the use of the tool. Likewise, derivative works are often largely reproductions with minor variations and are protected under fair use. A model that takes enormous amounts of data and dist…

In the history of media law I’ve seen judged lean into whatever interpretation balances the ecosystem more than what is “literally the law”. The law is meant to serve people not the other way around. I hope judges will understand the contribution and theft can’t just be “haha fuck humanity love, openAI”

Ok, what about the open source and research models? I wouldn’t wager much on openai keeping a lead indefinitely. Certainly not to establish case law on what’s a pretty new technology (at least in its current use)

Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset

#92

Post by jpe90 »

Would it be feasible to fine-tune a large, capable model (like the recent LIMA) on the source code (and maybe a few high quality libraries) of a niche language, such that it's much better at helping you write and understand it?

Imagine how many doors it would open if you could fine-tune models capable of writing language bindings for you and keeping them up to date.

Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset

#94

Post by quickthrower2 »

heliophobicdude wrote: post #47
quickthrower2 wrote: post #15

When is fine tuning worth it, rather than just prompt engineering?

I think these are two very separate concepts. What we are mostly seeing when it comes to fine-tuning is making a model promptable. Models like LLaMA or the original GPT3 weren't promptable. They were fine-tuned with demonstration data that looks like a prompt input, prompt output. See below: { "instruction": "What would be the output of the following JavaScript snippet?", "input": "let area = 6 * 5;\nlet radius = are…

Thanks for link 2 - it is worth a proper read! Read half of it already and it is very interesting and useful for understanding this.

Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset

#95

Post by belter »

itake wrote: post #69
tsunamifury wrote: post #68

Earlier quoted context omitted.

You understand these things have a very very wide interpretation scope here that has yet to be tested in court. I wouldn’t make these statements so confidently as courts tend to reinterpret the law significantly for the balance of societal factors when serious technology changes occur.

AI generated work is not copyright-able. I guess the courts later could disagree though. https://www.copyright.gov/ai/

If the AI generates a new Eric Clapton album, with the same similar voice and guitar playing style?

Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset

#97

Post by heliophobicdude »

quickthrower2 wrote: post #94
heliophobicdude wrote: post #47

Earlier quoted context omitted.

I think these are two very separate concepts. What we are mostly seeing when it comes to fine-tuning is making a model promptable. Models like LLaMA or the original GPT3 weren't promptable. They were fine-tuned with demonstration data that looks like a prompt input, prompt output. See below: { "instruction": "What would be the output of the following JavaScript snippet?", "input": "let area = 6 * 5;\nlet radius = are…

Thanks for link 2 - it is worth a proper read! Read half of it already and it is very interesting and useful for understanding this.

Cheers!

Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset

#98

Post by t-vi »

stoptrlling wrote: post #87

Anyone knows the computational cost of training with these LoRa designs? Given that we are talking about rates of token per seconds, it seems training a bigger dataset could be extremely expensive

The adapter and LoRa have a drastically fewer parameters, so one might expect that forward + backward is roughly 2x the cost of forward.

Then (as far as I know), in contrast to generation, training is done on the entire output of the transformer (so all tokens of the full input) rather than serially token-by-token (in the RNN days, this was called teacher-forcing), so that may give you a significant boost in the tokens per second rate over generation.

Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset

#99

Post by tazjin »

jpe90 wrote: post #92

Would it be feasible to fine-tune a large, capable model (like the recent LIMA) on the source code (and maybe a few high quality libraries) of a niche language, such that it's much better at helping you write and understand it? Imagine how many doors it would open if you could fine-tune models capable of writing language bindings for you and keeping them up to date.

Totally. GPT-4 can already do this, untuned, on niche languages and libraries. One of the main problems is still that you don't know when it's hallucinating a function or whatever though.

Re: How to Finetune GPT-Like Large Language Models on a Custom Dataset

#100

Post by asah »

cameldrv wrote: post #65
sp332 wrote: post #58

Earlier quoted context omitted.

It's against the terms of service to do the generation, but the generated text is not copyrighted. Those are different things.

GPT-4 is trained on a large number of web pages, some of which will have had their own terms of service.

see LinkedIn vs HiQ (which HiQ won) covering fair use of logged-out web pages.
Post reply on HN