Hacker News

apwheele
GLiNER2: Unified Schema-Based Information Extraction github.com

plaguna10 minutes ago

Is this only for text I guess? What if the documents are in PDF? What is the recommendation to transform PDF to text?

adsharma2 hours ago

Feels like it's written by ML people not following python software engineering practices.

No black, UV or ruff.

Prints messages with emojis to stdout by default.

Makes a connection to hugging face on every import.

https://github.com/fastino-ai/GLiNER2/pull/74

snthpy43 minutes ago

This looks great. Thank you!

iwhalen8 hours ago

Very cool stuff. Love the focus on CPU-first.

Would also love to see some throughput numbers on basic VM setup.

Edit: there are some latency numbers in the paper https://arxiv.org/pdf/2507.18546

deepsquirrelnet8 hours ago

Zero-shot encoder models are so cool. I'll definitely be checking this out.

If you're looking for a zero-shot classifier, tasksource is in a similar vein.

https://huggingface.co/tasksource/ModernBERT-large-nli

hbcondo7148 hours ago

There is another version at:

https://github.com/urchade/GLiNER

Looks like it’s still being maintained too?

adsharma2 hours ago

Use Gliner2. Much better model.

hn-front (c) 2024 voximity
source