Add trained VNTC model and usage demonstration script

- Upload sklearn_model.joblib (VNTC model, 92.33% accuracy) for Hugging Face Hub
- Add use_this_model.py to demonstrate model usage from Hub
- Model supports Vietnamese news classification across 10 categories

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

sklearn_model.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b25b914bfacc590165e0ce35e944815cf1fda52d9d2fadf79334c5bc2754b360
+size 2393144

use_this_model.py

@@ -0,0 +1,198 @@
+#!/usr/bin/env python3
+"""
+Demonstration script for using Sonar Core 1 models from Hugging Face Hub.
+Shows how to download and use the pre-trained Vietnamese text classification model.
+"""
+
+from huggingface_hub import hf_hub_download
+import joblib
+import numpy as np
+
+
+def load_model_from_hub():
+    """Load the pre-trained model from Hugging Face Hub"""
+    try:
+        print("Downloading model from Hugging Face Hub...")
+        model_path = hf_hub_download("undertheseanlp/sonar_core_1", "sklearn_model.joblib")
+        print(f"Model downloaded to: {model_path}")
+
+        print("Loading model...")
+        model = joblib.load(model_path)
+        return model
+    except Exception as e:
+        print(f"Error downloading from Hub: {e}")
+        print("\nFalling back to local model for demonstration...")
+
+        # Try to find local model
+        from pathlib import Path
+        runs_dir = Path("runs")
+        if runs_dir.exists():
+            run_dirs = [d for d in runs_dir.iterdir() if d.is_dir()]
+            run_dirs.sort()
+
+            for run_dir in reversed(run_dirs):
+                models_dir = run_dir / "models"
+                if models_dir.exists():
+                    for model_file in models_dir.glob("*.pkl"):
+                        if "VNTC" in model_file.name:
+                            print(f"Using local model: {model_file}")
+                            return joblib.load(model_file)
+
+        raise FileNotFoundError("No model available. Please upload model to Hugging Face Hub or train locally.")
+
+
+def predict_vntc_examples(model):
+    """Demonstrate predictions on VNTC (news) examples"""
+    print("\n" + "="*60)
+    print("VIETNAMESE NEWS CLASSIFICATION EXAMPLES")
+    print("="*60)
+
+    # Vietnamese news examples for different categories
+    examples = [
+        ("Chính trị & Xã hội", "Chính phủ đã thông qua nghị định mới về chính sách xã hội"),
+        ("Đời sống", "Xu hướng ăn uống lành mạnh đang được nhiều người quan tâm"),
+        ("Khoa học", "Các nhà khoa học đã phát hiện ra loại vi khuẩn mới"),
+        ("Kinh doanh", "Thị trường chứng khoán có nhiều biến động trong tuần qua"),
+        ("Pháp luật", "Luật an toàn giao thông sẽ có hiệu lực từ tháng sau"),
+        ("Sức khỏe", "Tiêm vaccine phòng chống COVID-19 đã đạt tỷ lệ cao"),
+        ("Thế giới", "Hội nghị thượng đỉnh quốc tế sẽ diễn ra tại Geneva"),
+        ("Thể thao", "Đội tuyển bóng đá Việt Nam giành chiến thắng 2-0"),
+        ("Văn hóa", "Lễ hội truyền thống sẽ được tổ chức vào cuối tuần"),
+        ("Vi tính", "Công nghệ trí tuệ nhân tạo đang phát triển mạnh mẽ")
+    ]
+
+    print("Testing Vietnamese news classification:")
+    print("-" * 60)
+
+    for expected_category, text in examples:
+        try:
+            prediction = model.predict([text])[0]
+            probabilities = model.predict_proba([text])[0]
+            confidence = np.max(probabilities)
+
+            print(f"Text: {text}")
+            print(f"Expected: {expected_category}")
+            print(f"Predicted: {prediction}")
+            print(f"Confidence: {confidence:.3f}")
+
+            # Show top 3 predictions
+            if hasattr(model, 'classes_'):
+                top_indices = np.argsort(probabilities)[-3:][::-1]
+                print("Top 3 predictions:")
+                for i, idx in enumerate(top_indices, 1):
+                    category = model.classes_[idx]
+                    prob = probabilities[idx]
+                    print(f"  {i}. {category}: {prob:.3f}")
+
+            print("-" * 60)
+
+        except Exception as e:
+            print(f"Error predicting '{text[:30]}...': {e}")
+            print("-" * 60)
+
+
+def interactive_mode(model):
+    """Interactive mode for testing custom text"""
+    print("\n" + "="*60)
+    print("INTERACTIVE MODE - VIETNAMESE TEXT CLASSIFICATION")
+    print("="*60)
+    print("Enter Vietnamese text to classify (type 'quit' to exit):")
+
+    while True:
+        try:
+            user_input = input("\nText: ").strip()
+
+            if user_input.lower() in ['quit', 'exit', 'q']:
+                break
+
+            if not user_input:
+                continue
+
+            prediction = model.predict([user_input])[0]
+            probabilities = model.predict_proba([user_input])[0]
+            confidence = np.max(probabilities)
+
+            print(f"Predicted category: {prediction}")
+            print(f"Confidence: {confidence:.3f}")
+
+            # Show top 3 predictions
+            if hasattr(model, 'classes_'):
+                top_indices = np.argsort(probabilities)[-3:][::-1]
+                print("Top 3 predictions:")
+                for i, idx in enumerate(top_indices, 1):
+                    category = model.classes_[idx]
+                    prob = probabilities[idx]
+                    print(f"  {i}. {category}: {prob:.3f}")
+
+        except KeyboardInterrupt:
+            print("\nExiting...")
+            break
+        except Exception as e:
+            print(f"Error: {e}")
+
+
+def simple_usage_example():
+    """Show simple usage example"""
+    print("\n" + "="*60)
+    print("SIMPLE USAGE EXAMPLE")
+    print("="*60)
+
+    print("Code example:")
+    print("""
+from huggingface_hub import hf_hub_download
+import joblib
+
+# Download and load model
+model = joblib.load(
+    hf_hub_download("undertheseanlp/sonar_core_1", "sklearn_model.joblib")
+)
+
+# Make prediction
+text = "Việt Nam giành chiến thắng trong trận bán kết"
+prediction = model.predict([text])[0]
+probabilities = model.predict_proba([text])[0]
+
+print(f"Predicted category: {prediction}")
+print(f"Confidence: {max(probabilities):.3f}")
+""")
+
+
+def main():
+    """Main demonstration function"""
+    print("Sonar Core 1 - Hugging Face Hub Model Usage")
+    print("=" * 60)
+
+    try:
+        # Load model from Hugging Face Hub
+        model = load_model_from_hub()
+
+        # Show simple usage example
+        simple_usage_example()
+
+        # Run prediction examples
+        predict_vntc_examples(model)
+
+        # Check if we're in an interactive environment
+        try:
+            # Try to get input to see if we can run interactive mode
+            import sys
+            if hasattr(sys, 'ps1') or sys.stdin.isatty():
+                response = input("\nWould you like to try interactive mode? (y/n): ")
+                if response.lower().startswith('y'):
+                    interactive_mode(model)
+        except (EOFError, OSError):
+            print("\nInteractive mode not available in this environment.")
+            print("Run this script in a regular terminal to use interactive mode.")
+
+        print("\nDemonstration complete!")
+
+    except ImportError:
+        print("Error: huggingface_hub is required. Install with:")
+        print("  pip install huggingface_hub")
+    except Exception as e:
+        print(f"Error loading model: {e}")
+        print("\nMake sure you have internet connection and try again.")
+
+
+if __name__ == "__main__":
+    main()