Training a 3.8B LLM to 0.384 CORE for $998 – Hugo Vergnes

AAnon84 about 3 hours ago 3 commentsRead Article on hugovergnes.github.io

ZH version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

100% Positive

Analyzed from 72 words in the discussion.

Discussion (3 Comments)Read Original on HackerNews

johnnylambada•38 minutes ago

I don’t blame you for using an LLM to write an article about an LLM that you built. I’ve been reading so much LLM output that now I see it everywhere. I wonder if humans will start writing more like LLMs?

brainless•1 minute ago

When we hyper focus on finding something, we find it all the time.

The world of tiny LLMs is so interesting. It is unlocking novel ways to encode information. Why focus on the style of writing instead of the subject matter?

vatsachak•about 1 hour ago

Very cool. I wonder what's the minimum amount of money you'd need to get it to score well on AIME