I’ve been experimenting with a local approach to some of the classification tasks people are using Jev for. This approach uses text embeddings + logistic regression On Banking77, which contains 77 categories of banking support questions, I get 94. 25% using bge-large-en-v1.

Source: [Hacker News](https://gist.github.com/nicobrenner/056a5aaff5d0119c0032ecdad5029557)

Sponsored