Update README.md

README.md

@@ -42,22 +42,19 @@ label_list = ["O", "B-PER", "I-PER", "B-ORG", "I-ORG", "B-LOC", "I-LOC", "B-MISC
 
 ```
 def predict_entities(text, model):
-    # ✅ Tokenize input text
+
     tokens = tokenizer(text, return_tensors="pt", truncation=True)
     tokens = {key: val.to(device) for key, val in tokens.items()}  # Move to CUDA
 
-    # ✅ Run model inference
     with torch.no_grad():
         outputs = model(**tokens)
     
     logits = outputs.logits  # Extract logits
     predictions = torch.argmax(logits, dim=2)  # Get highest probability labels
 
-    # ✅ Convert token IDs back to words
     tokens_list = tokenizer.convert_ids_to_tokens(tokens["input_ids"][0])
     predicted_labels = [label_list[pred] for pred in predictions[0].cpu().numpy()]
 
-    # ✅ Group subword tokens into whole words
     final_tokens = []
     final_labels = []
     for token, label in zip(tokens_list, predicted_labels):
@@ -67,7 +64,6 @@ def predict_entities(text, model):
             final_tokens.append(token)
             final_labels.append(label)
 
-    # ✅ Display results (ignore special tokens)
     for token, label in zip(final_tokens, final_labels):
         if token not in ["[CLS]", "[SEP]"]:
             print(f"{token}: {label}")