Create README.md

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+language:
+- fa
+metrics:
+- f1
+- accuracy
+base_model:
+- myrkur/Persian-ModernBert-base
+library_name: transformers
+---
+
+# ModernBERT-base-fa-taghche
+
+Fine-tuned Persian sentiment analysis model based on [`myrkur/Persian-ModernBert-base`](https://huggingface.co/myrkur/Persian-ModernBert-base) for binary sentiment classification on the Taaghche Persian review dataset.
+
+## Dataset
+
+The model was trained on the Taaghche Persian reviews dataset available on Kaggle:
+
+* [Taaghche Dataset](https://www.kaggle.com/saeedtqp/taaghche)
+
+## Model Details
+
+* **Base model:** `myrkur/Persian-ModernBert-base`
+* **Task:** Sentiment Classification
+* **Language:** Persian (Farsi)
+* **Framework:** Transformers + PyTorch
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model_name = "aysangh/ModernBERT-base-fa-taghche"
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+def predict_sentiment(text):
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, max_length=256, padding=True)
+    with torch.no_grad():
+        outputs = model(**inputs)
+    probs = torch.softmax(outputs.logits, dim=-1)
+    pred = torch.argmax(probs, dim=-1).item()
+    confidence = probs[0][pred].item()
+    return {
+    "label": "positive" if pred == 0 else "negative",
+    "confidence": confidence
+}
+
+text = "خیلی بد بود، اصلاً پیشنهاد نمی‌کنم."
+
+result = predict_sentiment(text)
+print(result)
+
+# Output:
+# {'label': 'negative', 'confidence': 0.9999935626983643}
+```
+
+## Repository
+
+Training and inference scripts are available on [GitHub](https://github.com/aysangh/persian-sentiment-analysis).