Show HN: A local alternative to Jev – 94% on Banking77

Show HN: A local alternative to Jev – 94% on Banking77 Instantly share code, notes, and snippets. nicobrenner / banking77_gist.py Last active September 26, 2026 16:53 Show Gist options Download ZIP Star 0 ( 0 ) You must be signed in to star a gist Fork 0 ( 0 ) You must be signed in to fork a gist Clone this repository at <script src="https://gist.github.com/nicobrenner/056a5aaff5d0119c0032ecdad5029557.js"></script> Save nicobrenner/056a5aaff5d0119c0032ecdad5029557 to your computer and use it in GitHub Desktop.

This Other is relevant to the technology intelligence record because it involves GitHub. The source article should remain the factual reference for follow-up coverage.

• Instantly share code, notes, and snippets.
• nicobrenner / banking77_gist.py Last active September 26, 2026 16:53 Show Gist options Download ZIP Star 0 ( 0 ) You must be signed in to star a gist Fork 0 ( 0 ) You must be signed in to fork a gist Clone this repository at <script src="https://gist.github.com/nicobrenner/056a5aaff5d0119c0032ecdad5029557.js"></script> Save nicobrenner/056a5aaff5d0119c0032ecdad5029557 to your computer and use it in GitHub Desktop.
• Clone this repository at <script src="https://gist.github.com/nicobrenner/056a5aaff5d0119c0032ecdad5029557.js"></script> Save nicobrenner/056a5aaff5d0119c0032ecdad5029557 to your computer and use it in GitHub Desktop.
• Download ZIP Banking77: 94.25% accuracy with a 642 KB logistic classifier (embeddings + sklearn) Raw banking77_gist.py #!/usr/bin/env python3 """ Banking77: frozen embeddings + logistic regression for 77-class intent detection.
• Uses the Banking77 dataset (3,080 test queries across 77 banking intents) to show what a simple pipeline can do: convert text to vectors with a pre-trained embedding model, then train an sklearn LogisticRegression on top.
• The embedding model is used as-is — no fine-tuning, no GPU needed.