Update README.md

README.md

@@ -47,24 +47,125 @@ group
 
 
 ```python
-Loading the Model
+#Loading the Model
 
 from transformers import DistilBertForTokenClassification, DistilBertTokenizerFast
 import torch
 
-def load_model_and_tokenizer(model_path):
-    tokenizer = DistilBertTokenizerFast.from_pretrained('distilbert-base-uncased')
-    model = DistilBertForTokenClassification.from_pretrained(model_path)
-    return model, tokenizer
-
-model_path = "./final_model"
-model, tokenizer = load_model_and_tokenizer(model_path)
-model.eval()
+model_name = "AventIQ-AI/distilbert-base-uncased_token_classification"
+
+def predict_entities(text, model, tokenizer):
+    """Predict Named Entities from the quantized model"""
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
+    
+    # Convert to FP32 if needed (for stability)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        predictions = torch.argmax(outputs.logits.float(), dim=2)  # Convert logits to float32
+    
+    predicted_labels = [model.config.id2label[t.item()] for t in predictions[0]]
+    tokens = tokenizer.convert_ids_to_tokens(inputs["input_ids"][0])
+
+    # Remove special tokens and align subwords
+    entities = []
+    current_entity = None
+
+    for token, label in zip(tokens, predicted_labels):
+        if token in [tokenizer.cls_token, tokenizer.sep_token, tokenizer.pad_token]:
+            continue
+            
+        if token.startswith("##"):  # Handle subwords
+            if current_entity:
+                current_entity["text"] += token[2:]
+            continue
+            
+        if label == "O":
+            if current_entity:
+                entities.append(current_entity)
+                current_entity = None
+        else:
+            if label.startswith("B-"):
+                if current_entity:
+                    entities.append(current_entity)
+                current_entity = {"text": token, "type": label[2:]}
+            elif label.startswith("I-") and current_entity:
+                current_entity["text"] += " " + token
+
+    if current_entity:
+        entities.append(current_entity)
+
+    return entities
 ```
 
 # Example Usage
+```python
+test_sentence = ["Apple CEO Tim Cook announced the new iPhone 14 at their headquarters in Cupertino."]
+for sentence in test_sentences:
+    print(f"\nInput: {sentence}")
+    entities = predict_entities(sentence, model, tokenizer)
+    print("Detected entities:")
+    for entity in entities:
+        print(f"- {entity['text']} ({entity['type']})")
+    print("-" * 50)
+```
+
+## 📊 Evaluation Results for Quantized Model
+ 
+### **🔹 Overall Performance**
+ 
+- **Accuracy**: **97.10%** ✅
+- **Precision**: **89.52%**
+- **Recall**: **90.67%**
+- **F1 Score**: **90.09%**
+ 
+---
+ 
+### **🔹 Performance by Entity Type**
+ 
+| Entity Type | Precision | Recall | F1 Score | Number of Entities |
+|------------|-----------|--------|----------|--------------------|
+| **LOC** (Location) | **91.46%** | **92.07%** | **91.76%** | 3,000 |
+| **MISC** (Miscellaneous) | **71.25%** | **72.83%** | **72.03%** | 1,266 |
+| **ORG** (Organization) | **89.83%** | **93.02%** | **91.40%** | 3,524 |
+| **PER** (Person) | **95.16%** | **94.04%** | **94.60%** | 2,989 |
+
+ ---
+#### ⏳ **Inference Speed Metrics**
+- **Total Evaluation Time**: 15.89 sec
+- **Samples Processed per Second**: 217.26
+- **Steps per Second**: 27.18
+- **Epochs Completed**: 3
+ 
+---
+## Fine-Tuning Details
+### Dataset
+The Hugging Face's `wnut_17` dataset was used, containing texts and their ner tags.
+
+## 📊 Training Details
+- **Number of epochs**: 3  
+- **Batch size**: 16 
+- **Evaluation strategy**: epoch
+- **Learning Rate**: 2e-5
+
+### ⚡ Quantization
+Post-training quantization was applied using PyTorch's built-in quantization framework to reduce the model size and improve inference efficiency.
+
+---
+## 📂 Repository Structure
+```
+.
+├── model/               # Contains the quantized model files
+├── tokenizer_config/    # Tokenizer configuration and vocabulary files
+├── model.safetensors/   # Quantized Model
+├── README.md            # Model documentation
+```
+
+---
+## ⚠️ Limitations
+- The model may not generalize well to domains outside the fine-tuning dataset.
+- Quantization may result in minor accuracy degradation compared to full-precision models.
 
-test_sentence = "Apple CEO Tim Cook announced the new iPhone 14 at their headquarters in Cupertino."
-entities = predict_entities(test_sentence, model, tokenizer)
-print(entities)
+---
+## 🤝 Contributing
+Contributions are welcome! Feel free to open an issue or submit a pull request if you have suggestions or improvements.