Hacker News Reader

BERT models are still amazing for what they do. Even the latest JEV/KEV/SEV/BEV/REV/TREV models can't beat a well-trained BERT.

View on HN

hehe, so much in a name... just today I told Claude off for recommending me a BERT model for voice identification and it told me it was actually SOTA 2025!

https://arxiv.org/html/2510.04213v1

do you have examples of open weight BERT models from hugging face which are trained for specific use cases?

For these small models, you would fine tune them on your use case. https://huggingface.co/transformers/v4.8.2/training.html

Reply on news.ycombinator.com