News for hackers. Stuff that matters.

A comment on GPU-Accelerated LLM on a $100 Orange Pi. Parent comment

Re:GPU-Accelerated LLM on a $100 Orange Pi by omneity on Tuesday August 15, 2023 @09:10AM (#37133554)
My hypothesis is that including information in the LLM’s prompt to support its answer changes the task roughly from text generation, very hallucination prone, to text summarization, or reformulation with some reasoning, and this is less likely to hallucinate.

That was my personal experience in general with ChatGPT as well as LLaMa1/2.

[ Parent | on HN ]
Re:GPU-Accelerated LLM on a $100 Orange Pi by jacquesm on Tuesday August 15, 2023 @09:40AM (#37133886)
A friend and colleague of mine just tried this and the first results are quite promising.
[ Parent | on HN ]