Update README.md
Browse files
README.md
CHANGED
|
@@ -14,9 +14,9 @@ tags:
|
|
| 14 |
- zero-shot
|
| 15 |
---
|
| 16 |
|
| 17 |
-
|
| 18 |
|
| 19 |
-
|
| 20 |
* a more powerful version of GLiNER-large-v2.1, surpassing it by **+4.5% on average**
|
| 21 |
* is trained on the **diverse dataset tailored for real-life use cases**
|
| 22 |
|
|
@@ -35,7 +35,7 @@ NuZero span is:
|
|
| 35 |
```python
|
| 36 |
from gliner import GLiNER
|
| 37 |
|
| 38 |
-
model = GLiNER.from_pretrained("numind/
|
| 39 |
|
| 40 |
# NuZero requires labels to be lower-cased!
|
| 41 |
labels = ["person", "award", "date", "competitions", "teams"]
|
|
|
|
| 14 |
- zero-shot
|
| 15 |
---
|
| 16 |
|
| 17 |
+
NuNerZero - 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).
|
| 18 |
|
| 19 |
+
NuNerZero span is:
|
| 20 |
* a more powerful version of GLiNER-large-v2.1, surpassing it by **+4.5% on average**
|
| 21 |
* is trained on the **diverse dataset tailored for real-life use cases**
|
| 22 |
|
|
|
|
| 35 |
```python
|
| 36 |
from gliner import GLiNER
|
| 37 |
|
| 38 |
+
model = GLiNER.from_pretrained("numind/NuNerZero_span")
|
| 39 |
|
| 40 |
# NuZero requires labels to be lower-cased!
|
| 41 |
labels = ["person", "award", "date", "competitions", "teams"]
|