14:42
2026-09-30
github.com
natural-language-processing
Show HN: Offlineisbetter: Efficient Models for Text on CPU
Offlineisbetter released offline-sentiment-small, a 230M-parameter text model for sentiment analysis that runs on CPU, claiming an F1 of 0.9489 on the stanfordnlp/sst2 validation set at a p95 latency …