Show HN: A local alternative to Jev – 94% on Banking77https://gist.github.com/nicobrenner/056a5aaff5d0119c0032ecdad5029557
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-v1.5 for embeddings, and 93.28% with all-MiniLM-L6-v2 (only the classifier gets trained, the embeddings model stays unchanged). For comparison: Model Accuracy Size/training time - IntenDD (SOTA): 94.86% (~350M params, hours on GPU) - This script: 94.25% (642 KB classifier, 3s on CPU) - ModernBERT fine-tuned: 93.99% (149M para…
