Ask HN: Has any one tried fine tuning GPT 3.5

Re:Ask HN: Has any one tried fine tuning GPT 3.5 by fbnbr on Tuesday September 26, 2023 @11:35PM (#37669694)

I noticed this really depends on how much data you provide but it’s still cheaper than doing llama2 yourself

[ Parent | on HN ]

Re:Ask HN: Has any one tried fine tuning GPT 3.5 by capableweb on Wednesday September 27, 2023 @08:42AM (#37673789)

> but it’s still cheaper than doing llama2 yourself

How you calculate this? Unless you're factoring in acquiring the hardware, you can usually get away with outsourcing the training of llama2 to rented hardware, and then run it on owned hardware, so with lots of executions, using llama2 locally should most definitely be cheaper in the medium to long term, compared to paying for the training + execution of fine tuned GPT3.5

[ Parent | on HN ]