GLiNER2: Unified Schema-Based Information Extraction
1–10 of 15 posts
Re: GLiNER2: Unified Schema-Based Information Extraction
#2There is another version at:
https://github.com/urchade/GLiNER
Looks like it’s still being maintained too?
Re: GLiNER2: Unified Schema-Based Information Extraction
#3Zero-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.
Re: GLiNER2: Unified Schema-Based Information Extraction
#4Very 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
Re: GLiNER2: Unified Schema-Based Information Extraction
#5There is another version at: https://github.com/urchade/GLiNER Looks like it’s still being maintained too?
Use Gliner2. Much better model.
Re: GLiNER2: Unified Schema-Based Information Extraction
#6Feels 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.
Re: GLiNER2: Unified Schema-Based Information Extraction
#7This looks great. Thank you!
Re: GLiNER2: Unified Schema-Based Information Extraction
#8Is this only for text I guess? What if the documents are in PDF? What is the recommendation to transform PDF to text?
Re: GLiNER2: Unified Schema-Based Information Extraction
#9Feels 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
GLiNER is a really great research work. But putting this kind of things in production is just another job. Not trying to do self promotion here, but there are alternatives for this purpose, like gline-rs (https://github.com/fbilhaut/gline-rs). Support of GLiNER 2 models is on the way.
Re: GLiNER2: Unified Schema-Based Information Extraction
#10Is this only for text I guess? What if the documents are in PDF? What is the recommendation to transform PDF to text?