Update README.md

README.md

@@ -5,7 +5,61 @@ tags: []
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+---
+language: ms
+license: mit
+tags:
+  - text-classification
+  - malay
+  - fine-tuned
+  - transformers
+  - bert
+  - multi-class
+datasets:
+  - custom
+model-index:
+  - name: malay_classification
+    results: []
+---
+
+# 🇲🇾 Malay News Classification Model
+
+This is a fine-tuned `rmtariq/ft-Malay-bert` model built to classify **Malay news headlines** into 7 topics:
+
+- `bisnes`
+- `dunia`
+- `hiburan`
+- `jenayah`
+- `kemalangan`
+- `politik`
+- `semasa`
+
+## 📊 Dataset
+
+Fine-tuned on a custom dataset with ~3,000 news headlines labeled by topic.
+
+| Label        | Examples |
+|--------------|----------|
+| bisnes       | ✔️ sufficient |
+| dunia        | ⚠️ very few |
+| hiburan      | ⚠️ very few |
+| jenayah      | ✔️ good |
+| kemalangan   | ⚠️ very few |
+| politik      | ✔️ good |
+| semasa       | ✔️ good |
+
+## 🧠 Base Model
+
+Fine-tuned from [`rmtariq/ft-Malay-bert`](https://huggingface.co/rmtariq/ft-Malay-bert), originally trained for sentiment analysis on Malay text.
+
+## 🧪 Example Inference
+
+```python
+from transformers import pipeline
+
+clf = pipeline("text-classification", model="rmtariq/malay_classification")
+clf("Kerajaan akan memperkenalkan cukai khas minyak sawit mentah")
+