News for hackers. Stuff that matters.
Re:GPT-3.5 Turbo fine-tuning and API updates by easygenes on Tuesday August 22, 2023 @11:58PM (#37231689)
For what tasks do you consider 70B beyond GPT-3.5 performance? There are some I’m aware of, but they are very much the exception and not the rule, even with the best 70B fine-tunes currently available.
Re:GPT-3.5 Turbo fine-tuning and API updates by syntaxing on Wednesday August 23, 2023 @07:04AM (#37234117)
I mainly use 70B for “text QA” on files I find sensitive like personal documents. The answers have been very close to what I get if I use GPT-3 (langchain makes it easy to switch). Do you use the quantized version? If so, try running the full one on a A100.