Update README.md

README.md

@@ -1,69 +1,81 @@
 ---
-library_name: transformers
+language:
+- ur
 license: apache-2.0
-base_model: bert-base-multilingual-cased
 tags:
-- generated_from_trainer
+- text-classification
+- sentiment-analysis
+- urdu
+- bert
+- fine-tuned
+- nlp
+datasets:
+- mirfan899/imdb_urdu_reviews
 metrics:
 - accuracy
 - f1
 model-index:
 - name: urdu-sentiment-classifier
-  results: []
+  results:
+  - task:
+      type: text-classification
+    dataset:
+      name: IMDB Urdu Reviews
+      type: mirfan899/imdb_urdu_reviews
+    metrics:
+    - type: accuracy
+      value: 0.81
+    - type: f1
+      value: 0.8098
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
+# Urdu Sentiment Classifier 🇵🇰
 
-# urdu-sentiment-classifier
+A fine-tuned **bert-base-multilingual-cased** model for **Urdu sentiment analysis** — classifying Urdu text as positive or negative.
 
-This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.0358
-- Accuracy: 0.8074
-- F1: 0.8073
+## Live Demo
 
-## Model description
+ [Try it on HuggingFace Spaces](https://huggingface.co/spaces/H-Layba/urdu-sentiment-classifier)
 
-More information needed
+## Performance
 
-## Intended uses & limitations
+| Metric | Score |
+|--------|-------|
+| Accuracy | 81.00% |
+| F1 Score (weighted) | 0.8098 |
 
-More information needed
+## Example Predictions
 
-## Training and evaluation data
+```python
+from transformers import pipeline
 
-More information needed
+classifier = pipeline("text-classification", model="H-Layba/urdu-sentiment-classifier")
 
-## Training procedure
+classifier("یہ فلم بہت اچھی تھی")
+# [{'label': 'positive', 'score': 0.9936}]
 
-### Training hyperparameters
+classifier("آج کا دن بہت برا تھا")
+# [{'label': 'negative', 'score': 0.9918}]
+```
 
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 64
-- eval_batch_size: 128
-- seed: 42
-- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 100
-- num_epochs: 5
-- mixed_precision_training: Native AMP
+## Training Details
 
-### Training results
+- **Base model:** bert-base-multilingual-cased
+- **Dataset:** 50,000 Urdu movie reviews
+- **Epochs:** 5
+- **Learning rate:** 2e-5
+- **Batch size:** 32 (train), 64 (eval)
+- **Hardware:** Kaggle T4 GPU
+- **Mixed precision:** fp16
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.8904        | 1.0   | 625  | 0.9830          | 0.7664   | 0.7622 |
-| 0.7935        | 2.0   | 1250 | 0.8413          | 0.7978   | 0.7975 |
-| 0.6253        | 3.0   | 1875 | 0.9115          | 0.8021   | 0.8014 |
-| 0.5877        | 4.0   | 2500 | 0.9304          | 0.8055   | 0.8051 |
-| 0.4309        | 5.0   | 3125 | 1.0358          | 0.8074   | 0.8073 |
+## Dataset
 
+Trained on `mirfan899/imdb_urdu_reviews` — 50,000 Urdu translations of IMDB movie reviews with positive/negative sentiment labels.
 
-### Framework versions
+## Part of Urdu NLP Suite
 
-- Transformers 5.0.0
-- Pytorch 2.10.0+cu128
-- Datasets 4.8.5
-- Tokenizers 0.22.2
+This model is part of a larger collection of fine-tuned Urdu NLP models:
+- [x] Sentiment Classification ← this model
+- [ ] Text Summarization
+- [ ] Question Answering  
+- [ ] Urdu → English Translation