Mistral Small 3

Re:Mistral Small 3 by pheeney on Thursday January 30, 2025 @12:55PM (#42880208)

What models would you recommend for basic classification if you don't need a 24B parameter one?

[ Parent | on HN ]

Re:Mistral Small 3 by josh-sematic on Thursday January 30, 2025 @01:51PM (#42880833)

You might find this comparison chart helpful: https://www.airtrain.ai/blog/how-15-top-llms-perform-on-clas...

Note: from October; also I work at Airtrain

[ Parent | on HN ]

Re:Mistral Small 3 by Beretta_Vexee on Friday January 31, 2025 @04:06AM (#42885931)

There's no alternative to testing with your own data. The majority of our data is in French, and our benchmarks differ greatly from public benchmarks generally based on English documents.

[ Parent | on HN ]

Re:Mistral Small 3 by elorant on Friday January 31, 2025 @08:32AM (#42887450)

I’m using Llama-3 8B to classify html files. It’s surprisingly good, and I run it on an RTX 4060 Ti at 8-bit quantization. No complains so far.

[ Parent | on HN ]