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

11–20 of 126 posts

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

#11

Post by cookieperson »

montenegrohugo wrote: post #3
artembugara wrote: post #2

Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"

Yup, totally. This is a form of knowledge distillation. Openai, or other foundational model providers, can't really do anything about it.

Well they can sue you and bankrupt you by delaying trial for a decade. That's how the US patent system works anyways...

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

#13

Post by vlovich123 »

fallingmeat wrote: post #6
artembugara wrote: post #2

Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"

That is against their ToS though if you use your new LLM commercially.

And yet they trained theirs on commercial content on the internet. If that’s legal I doubt their argument holds up in court right?

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

#16

Post by dingledork69 »

artembugara wrote: post #10
fallingmeat wrote: post #6

Earlier quoted context omitted.

That is against their ToS though if you use your new LLM commercially.

As far as I remember, I fully own all the right to the output of OpenAI (for example).

I wonder how they reconcile naming themselves "Open"AI, telling people that generated works can be used however they please, except for training a potential competitor.

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

#17

Post by foobarbecue »

artembugara wrote: post #2

Have a question to the Generative AI experts here. So, I can use smthg like GPT-4 to label data and then use that as a train set for my own LLM, right? EDIT: adding this from OpenAI Restriction TOS: "(iii) use output from the Services to develop models that compete with OpenAI;"

Is "ca" "can" or "can't"?

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

#20

Post by tstrimple »

quickthrower2 wrote: post #15

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

From what I've seen, it's when embeddings get too large for the token limit or the embeddings drive the cost up too much because you're always operating near the max token limit. In those cases, it may be worth the up front training cost and slightly higher per-token cost to dramatically reduce the amount of tokens in the average request. If you're building a higher throughput solution, the difference in cost can be quite large.
Post reply on HN