News for hackers. Stuff that matters.

A comment on GPT-3.5 Turbo fine-tuning and API updates. Parent comment

Re:GPT-3.5 Turbo fine-tuning and API updates by kuida0r3 on Wednesday August 23, 2023 @08:53AM (#37235070)
Andrew Ng's deeplearning.ai just released a course on this yesterday https://www.deeplearning.ai/short-courses/finetuning-large-l... - at a high level it lets one put more data into the model than fits into the prompt.

And yes your use case of a large private knowledge base is one of the prime examples she used in the course. Scenarios that are domain-specific or privacy conscious probably makes more sense for finetuning as opposed to prompting.

[ Parent | on HN ]
Re:GPT-3.5 Turbo fine-tuning and API updates by OthmaneHamzaoui on Wednesday August 23, 2023 @03:32PM (#37241035)
But can't you still achieve domain-specific or privacy conscious cases by using retrieval + vector dbs?
[ Parent | on HN ]
Re:GPT-3.5 Turbo fine-tuning and API updates by kuida0r3 on Wednesday August 23, 2023 @05:50PM (#37242329)
Not an expert but my understanding is retrieval+vector db enables accurate information retrieval, whereas finetuning is more focused on specific task performance and generating coherent text (maybe in a different style) generally.
[ Parent | on HN ]