numind
/

NuNER_Zero-4k

Token Classification

entity recognition

named entity recognition

Model card Files Files and versions Community

Serega6678 commited on Apr 29

Commit

48dbaf6

•

1 Parent(s): 3b046ee

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ tags:
 NuZero - is the family of Zero-Shot Entity Recognition models inspired by [GLiNER](https://huggingface.co/papers/2311.08526) and built with insights we gathered throughout our work on [NuNER](https://huggingface.co/collections/numind/nuner-token-classification-and-ner-backbones-65e1f6e14639e2a465af823b).
-The key difference between NuZero Token Long in comparison to GLiNER are:
 * **4096 context window!** vs 512 context. This allows processing a page at time vs a paragraph!
 * The possibility to **detect entities that are longer than 12 tokens**, as NuZero Token operates on the token level rather than on the span level.
 * NuZero family is trained on the **diverse dataset tailored for real-life use cases**

 NuZero - is the family of Zero-Shot Entity Recognition models inspired by [GLiNER](https://huggingface.co/papers/2311.08526) and built with insights we gathered throughout our work on [NuNER](https://huggingface.co/collections/numind/nuner-token-classification-and-ner-backbones-65e1f6e14639e2a465af823b).
+The key differences between NuZero Token Long in comparison to GLiNER are:
 * **4096 context window!** vs 512 context. This allows processing a page at time vs a paragraph!
 * The possibility to **detect entities that are longer than 12 tokens**, as NuZero Token operates on the token level rather than on the span level.
 * NuZero family is trained on the **diverse dataset tailored for real-life use cases**