Re:GPT-3.5 Turbo fine-tuning and API updates
by zo1 on Wednesday August 23, 2023 @01:41AM
(#37232249)
Can we supply our own fine-tuned models?
Re:GPT-3.5 Turbo fine-tuning and API updates
by andrewmunn on Wednesday August 23, 2023 @01:03AM
(#37232069)
How do you keep the cost down?
Llama-2-70B is $1 / million tokens, which is the most cost-efficient on the market that I'm aware of.
[1] https://app.endpoints.anyscale.com/