Update model card: fix all repo references to new names
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ datasets:
|
|
| 17 |
|
| 18 |
## Model Summary
|
| 19 |
|
| 20 |
-
`nuha-mlm` is an Arabic BERT model pre-trained from scratch on Jordanian social media text using masked language modelling (MLM). It serves as the domain-adapted base for the NUHA classifier family — [`nuha-binary`](https://huggingface.co/thejosango/nuha-binary) and [`nuha-
|
| 21 |
|
| 22 |
Starting from a fresh vocabulary trained on the NUHA corpus rather than fine-tuning an existing Arabic BERT, the model is adapted to the vocabulary and linguistic patterns of colloquial Jordanian Arabic social media text.
|
| 23 |
|
|
@@ -25,12 +25,12 @@ Starting from a fresh vocabulary trained on the NUHA corpus rather than fine-tun
|
|
| 25 |
|
| 26 |
### Direct Use
|
| 27 |
|
| 28 |
-
`nuha-mlm` can be used for masked token prediction on Arabic social media text, or as a base model for fine-tuning downstream Arabic NLP tasks — particularly those involving informal Jordanian or Levantine Arabic.
|
| 29 |
|
| 30 |
```python
|
| 31 |
from transformers import pipeline
|
| 32 |
|
| 33 |
-
fill_mask = pipeline("fill-mask", model="thejosango/nuha-mlm")
|
| 34 |
results = fill_mask("هذه المرأة [MASK] جداً")
|
| 35 |
for r in results:
|
| 36 |
print(r["token_str"], r["score"])
|
|
@@ -38,7 +38,7 @@ for r in results:
|
|
| 38 |
|
| 39 |
### Downstream Use
|
| 40 |
|
| 41 |
-
The primary intended downstream use is fine-tuning for hate speech and gender-based violence detection using the NUHA dataset, as demonstrated by [`nuha-binary`](https://huggingface.co/thejosango/nuha-binary) and [`nuha-
|
| 42 |
|
| 43 |
### Out-of-Scope Use
|
| 44 |
|
|
|
|
| 17 |
|
| 18 |
## Model Summary
|
| 19 |
|
| 20 |
+
`nuha-jo-mlm` is an Arabic BERT model pre-trained from scratch on Jordanian social media text using masked language modelling (MLM). It serves as the domain-adapted base for the NUHA classifier family — [`nuha-jo-binary`](https://huggingface.co/thejosango/nuha-jo-binary) and [`nuha-jo-trinary-full`](https://huggingface.co/thejosango/nuha-jo-trinary-full) — and was developed as part of a **pilot proof-of-concept** for the NUHA project by the [Jordan Open Source Association (JOSA)](https://josa.ngo).
|
| 21 |
|
| 22 |
Starting from a fresh vocabulary trained on the NUHA corpus rather than fine-tuning an existing Arabic BERT, the model is adapted to the vocabulary and linguistic patterns of colloquial Jordanian Arabic social media text.
|
| 23 |
|
|
|
|
| 25 |
|
| 26 |
### Direct Use
|
| 27 |
|
| 28 |
+
`nuha-jo-mlm` can be used for masked token prediction on Arabic social media text, or as a base model for fine-tuning downstream Arabic NLP tasks — particularly those involving informal Jordanian or Levantine Arabic.
|
| 29 |
|
| 30 |
```python
|
| 31 |
from transformers import pipeline
|
| 32 |
|
| 33 |
+
fill_mask = pipeline("fill-mask", model="thejosango/nuha-jo-mlm")
|
| 34 |
results = fill_mask("هذه المرأة [MASK] جداً")
|
| 35 |
for r in results:
|
| 36 |
print(r["token_str"], r["score"])
|
|
|
|
| 38 |
|
| 39 |
### Downstream Use
|
| 40 |
|
| 41 |
+
The primary intended downstream use is fine-tuning for hate speech and gender-based violence detection using the NUHA dataset, as demonstrated by [`nuha-jo-binary`](https://huggingface.co/thejosango/nuha-jo-binary) and [`nuha-jo-trinary-full`](https://huggingface.co/thejosango/nuha-jo-trinary-full).
|
| 42 |
|
| 43 |
### Out-of-Scope Use
|
| 44 |
|