Live data from Hacker News

Llamafile Returns

blog.mozilla.ai

21–25 of 25 posts

Re: Llamafile Returns

#22
post #8

Earlier quoted context omitted.

s/are/was I don't know if you were informed but you realize that jart is no longer at Mozilla anymore and now at Google Inc?

jart, you are back at Google?

Yeah Google liked llamafile so much that they asked me to help them improve the LLM on their website too.

Re: Llamafile Returns

#23

Earlier quoted context omitted.

People are so uninformed, they don't know you are Mozilla AI's star employee.

I agree that the work they put out is A+ Whenever I see content produced by jart, it's always amazing.

sorry, I'm out of the loop. is this thread glazing a celebrity member commenting on an announcement from his own team to create hype?

what the fuck is wrong with this website

Re: Llamafile Returns

#24
While this is very cool and llamafiles are quite universal there is anyway a nuance for Window systems which is the size limit for a Windows executable which is 4Gb maximum. As LLM models are tend to be quite large this limit is reached pretty fast. So for such cases llamafile.exe will be required (which is also universal and runs everywhere). And at the end it could be just llama.cpp tools which released for all platforms + the LLM model file itself.

Re: Llamafile Returns

#25

Earlier quoted context omitted.

I agree that the work they put out is A+ Whenever I see content produced by jart, it's always amazing.

sorry, I'm out of the loop. is this thread glazing a celebrity member commenting on an announcement from his own team to create hype? what the fuck is wrong with this website

it sounds like you are
Post reply on HN