Instructions to use urchade/gliner_large-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- GLiNER
How to use urchade/gliner_large-v2 with GLiNER:
from gliner import GLiNER model = GLiNER.from_pretrained("urchade/gliner_large-v2") - Notebooks
- Google Colab
- Kaggle
How much better is v2 compared to v1?
#4
by nbroad - opened
No description provided.
Or maybe it is more about license. V1 = nc license, v2 = apache
It is mainly about licence. The performance is similar in zero-shot NER benchmark (around 55 avg in OOD dans 44 in 20 NER datasets https://arxiv.org/pdf/2311.08526.pdf)
multi v2 should be better than multi
you can also try v2.1