News for hackers. Stuff that matters.

A comment on Forget ChatGPT: why researchers now run small AIs on their laptops. Parent comment

Re:Forget ChatGPT: why researchers now run small AIs on thei... by senkora on Monday September 23, 2024 @09:03AM (#41625623)
I'll play around with it some more later. I was running llava-v1.5-7b-q4.llamafile which is the example that they recommend trying first at https://github.com/Mozilla-Ocho/llamafile

Groq looks interesting and might be a better option for me. Thank you.

[ Parent | on HN ]
Re:Forget ChatGPT: why researchers now run small AIs on thei... by senkora on Monday September 23, 2024 @01:31PM (#41628495)
I got better performance of 20.18 tokens per second using tinyllama-1.1b-chat-v1.0.Q8_0.llamafile from https://huggingface.co/Bojun-Feng/TinyLlama-1.1B-Chat-v1.0-l...

If anyone is reading this and had trouble with a larger model, that might be the one to try next.

[ Parent | on HN ]