RAG mainly, Feature extraction, tagging, Document and e-mail classification.
You don't need a 24B parameter to know whether the e-mail should go to accounting or customer support.
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.
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.