Update README.md

update readme file

README.md

@@ -2,6 +2,7 @@
 # SIMPLE EXAMPLE: How to Use Your Trained Model
 # ============================================================
 
+```python
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 
@@ -14,69 +15,77 @@ tokenizer = AutoTokenizer.from_pretrained(model_path)
 # Step 2: Put model in evaluation mode
 model.eval()
 
-# Step 3: Test on a simple example
-# The model was trained on MRPC (paraphrase detection task)
-# It takes two sentences and predicts if they are paraphrases (1) or not (0)
+# Step 3: Test on simple examples using a helper function
+
+def predict_paraphrase(sentence1, sentence2):
+    """
+    Predicts whether two sentences are paraphrases and returns prediction and confidence.
+    """
+    inputs = tokenizer(sentence1, sentence2, return_tensors="pt", 
+                       truncation=True, padding=True, max_length=128)
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        prediction = torch.argmax(logits, dim=1).item()
+        confidence = torch.softmax(logits, dim=1)[0].max().item()
+    return prediction, confidence
+
+def display_result(example_idx, sentence1, sentence2):
+    prediction, confidence = predict_paraphrase(sentence1, sentence2)
+    print("="*60)
+    print(f"EXAMPLE {example_idx} - Are these paraphrases?")
+    print("="*60)
+    print(f"Sentence 1: {sentence1}")
+    print(f"Sentence 2: {sentence2}")
+    print(f"Prediction: {'YES (paraphrases)' if prediction == 1 else 'NO (not paraphrases)'}")
+    print(f"Confidence: {confidence:.4f}")
+    print()
 
 # Example 1: Two sentences that ARE paraphrases
-sentence1 = "The cat is sleeping on the mat"
-sentence2 = "The cat is napping on the mat"
+sentence1_1 = "The cat is sleeping on the mat"
+sentence2_1 = "The cat is napping on the mat"
 
-# Tokenize the sentences
-inputs = tokenizer(sentence1, sentence2, return_tensors="pt", 
-                   truncation=True, padding=True, max_length=128)
-
-# Step 4: Make prediction
-with torch.no_grad():
-    outputs = model(**inputs)
-    logits = outputs.logits
-    prediction = torch.argmax(logits, dim=1).item()
-
-print("="*60)
-print("EXAMPLE 1 - Are these paraphrases?")
-print("="*60)
-print(f"Sentence 1: {sentence1}")
-print(f"Sentence 2: {sentence2}")
-print(f"Prediction: {'YES (paraphrases)' if prediction == 1 else 'NO (not paraphrases)'}")
-print(f"Confidence: {torch.softmax(logits, dim=1)[0].max().item():.4f}")
-print()
+display_result(1, sentence1_1, sentence2_1)
 
 # Example 2: Two sentences that are NOT paraphrases
-sentence1 = "The dog is barking loudly"
-sentence2 = "I love eating pizza"
+sentence1_2 = "The dog is barking loudly"
+sentence2_2 = "I love eating pizza"
 
-inputs = tokenizer(sentence1, sentence2, return_tensors="pt",
-                   truncation=True, padding=True, max_length=128)
+display_result(2, sentence1_2, sentence2_2)
 
-with torch.no_grad():
-    outputs = model(**inputs)
-    logits = outputs.logits
-    prediction = torch.argmax(logits, dim=1).item()
-
-print("="*60)
-print("EXAMPLE 2 - Are these paraphrases?")
-print("="*60)
-print(f"Sentence 1: {sentence1}")
-print(f"Sentence 2: {sentence2}")
-print(f"Prediction: {'YES (paraphrases)' if prediction == 1 else 'NO (not paraphrases)'}")
-print(f"Confidence: {torch.softmax(logits, dim=1)[0].max().item():.4f}")
 print("="*60)
 
-
-
-============================================================
-EXAMPLE 1 - Are these paraphrases?
-============================================================
-Sentence 1: The cat is sleeping on the mat
-Sentence 2: The cat is napping on the mat
-Prediction: YES (paraphrases)
-Confidence: 0.9998
-
-============================================================
-EXAMPLE 2 - Are these paraphrases?
-============================================================
-Sentence 1: The dog is barking loudly
-Sentence 2: I love eating pizza
-Prediction: NO (not paraphrases)
-Confidence: 0.9584
-============================================================
+# -----------------------
+# Try your own examples!
+# -----------------------
+# Uncomment and edit the sentences below to test your own custom examples:
+# user_sentence1 = "Your first sentence here."
+# user_sentence2 = "Your second sentence here."
+# display_result("USER", user_sentence1, user_sentence2)
+```
+
+# ------------------------------------------------------------
+# How to call/use this model:
+# ------------------------------------------------------------
+# 1. Make sure you have the saved model files in the directory 'optimized-bert-model'
+# 2. Run this script in your Python environment (with 'transformers' and 'torch' installed)
+# 3. Change the example sentences inside the code block above to your own inputs to test paraphrase detection
+# 4. The script prints whether the sentences are paraphrases and gives a confidence score
+
+# Sample Output:
+# ============================================================
+# EXAMPLE 1 - Are these paraphrases?
+# ============================================================
+# Sentence 1: The cat is sleeping on the mat
+# Sentence 2: The cat is napping on the mat
+# Prediction: YES (paraphrases)
+# Confidence: 0.9998
+#
+# ============================================================
+# EXAMPLE 2 - Are these paraphrases?
+# ============================================================
+# Sentence 1: The dog is barking loudly
+# Sentence 2: I love eating pizza
+# Prediction: NO (not paraphrases)
+# Confidence: 0.9584
+# ============================================================