684 points prettyblocks | 1 comments | 21 Jan 25 19:39 UTC | HN request time: 0.284s | source

I mean anything in the 0.5B-3B range that's available on Ollama (for example). Have you built any cool tooling that uses these models as part of your work flow?

Show context

sidravi1 ◴[22 Jan 25 03:04 UTC] No.42788468[source]▶

>>42784365 (OP) #

We fine-tuned a Gemma 2B to identify urgent messages sent by new and expecting mothers on a government-run maternal health helpline.

https://idinsight.github.io/tech-blog/blog/enhancing_materna...

replies(4): >>42788954 #>>42790308 #>>42793587 #>>42801392 #

1. Mumps ◴[22 Jan 25 15:06 UTC] No.42793587[source]▶

>>42788468 #

lovely application!

Genuine question: why not use (Modern)BERT instead for classification? (Is the json-output explanation so critical?)

↑

Ask HN: Is anyone doing anything cool with tiny language models?