Adding `safetensors` variant of this model

README.md

@@ -2,7 +2,7 @@
 language:
 - ar
 license: apache-2.0
-base_model: thejosango/nuha-ajp-mlm
+base_model: thejosango/nuha-jo-mlm
 tags:
 - bert
 - text-classification
@@ -12,20 +12,20 @@ tags:
 - binary-classification
 - pilot
 datasets:
-- thejosango/nuha-ajp-dataset
+- thejosango/nuha-dataset
 metrics:
 - f1
 - precision
 - recall
 model-index:
-- name: nuha-ajp-binary
+- name: nuha-jo-binary
   results:
   - task:
       type: text-classification
       name: Text Classification
     dataset:
       name: Jordanian NUHA Dataset
-      type: thejosango/nuha-ajp-dataset
+      type: thejosango/nuha-dataset
       config: binary
       split: validation
     metrics:
@@ -40,11 +40,11 @@ model-index:
       name: Recall
 ---
 
-# nuha-ajp-binary
+# nuha-jo-binary
 
 ## Model Summary
 
-`nuha-ajp-binary` is a binary Arabic text classifier that detects hate speech in Jordanian social media comments. It fine-tunes [`nuha-ajp-mlm`](https://huggingface.co/thejosango/nuha-ajp-mlm) — a domain-adapted Arabic BERT — and outputs one of two labels:
+`nuha-jo-binary` is a binary Arabic text classifier that detects hate speech in Jordanian social media comments. It fine-tunes [`nuha-jo-mlm`](https://huggingface.co/thejosango/nuha-jo-mlm) — a domain-adapted Arabic BERT — and outputs one of two labels:
 
 | Label | Meaning |
 |---|---|
@@ -53,7 +53,7 @@ model-index:
 
 This model was developed as part of a **pilot proof-of-concept** for the NUHA project by the [Jordan Open Source Association (JOSA)](https://josa.ngo). Performance metrics reflect the complexity of hate speech detection in colloquial Arabic and the exploratory nature of this initial effort.
 
-For a more granular three-class classifier, see [`nuha-ajp-trinary`](https://huggingface.co/thejosango/nuha-ajp-trinary).
+For a more granular three-class classifier, see [`nuha-jo-trinary`](https://huggingface.co/thejosango/nuha-jo-trinary).
 
 ## Uses
 
@@ -66,8 +66,8 @@ from transformers import pipeline
 
 classifier = pipeline(
     "text-classification",
-    model="thejosango/nuha-ajp-binary",
-    tokenizer="thejosango/nuha-ajp-binary",
+    model="thejosango/nuha-jo-binary",
+    tokenizer="thejosango/nuha-jo-binary",
 )
 
 result = classifier("أنتِ امرأة رائعة")
@@ -101,7 +101,7 @@ for comment, result in zip(comments, results):
 
 ### Training Data
 
-Fine-tuned on the `binary` configuration of [`thejosango/nuha-ajp-dataset`](https://huggingface.co/datasets/thejosango/nuha-ajp-dataset), which maps:
+Fine-tuned on the `binary` configuration of [`thejosango/nuha-dataset`](https://huggingface.co/datasets/thejosango/nuha-dataset), which maps:
 - **Not Online Violence** → `non-hate-speech`
 - **Offensive Language** → `hate-speech`
 - **Gender Based Violence** → `hate-speech`
@@ -122,7 +122,7 @@ At training and inference time, the following normalisation is applied to input
 
 | Parameter | Value |
 |---|---|
-| Base model | thejosango/nuha-ajp-mlm |
+| Base model | thejosango/nuha-jo-mlm |
 | Hidden layers | 4 (reduced from base's 12) |
 | Classifier dropout | 0.50 |
 | Learning rate | 5e-5 |
@@ -137,7 +137,7 @@ At training and inference time, the following normalisation is applied to input
 
 ### Evaluation Results
 
-Evaluated on the validation split of `thejosango/nuha-ajp-dataset` (binary configuration):
+Evaluated on the validation split of `thejosango/nuha-dataset` (binary configuration):
 
 | Metric | Value |
 |---|---|