Update README.md

README.md

@@ -1,4 +1,49 @@
 ---
 license: apache-2.0
 library_name: transformers
----
+---
+
+
+
+
+
+
+
+from transformers import BartTokenizer, BartForConditionalGeneration
+from datasets import load_dataset
+
+# Load pre-trained BART model for summarization
+tokenizer = BartTokenizer.from_pretrained('ayjays132/EnhancerModel')
+model = BartForConditionalGeneration.from_pretrained('ayjays132/EnhancerModel')
+
+# Load dataset
+dataset = load_dataset("cnn_dailymail", "3.0.0")
+
+# Function to generate summary
+def summarize(text):
+    inputs = tokenizer(text, return_tensors="pt", max_length=1024, truncation=True)
+    summary_ids = model.generate(inputs['input_ids'], max_length=150, min_length=40, length_penalty=2.0, num_beams=4, early_stopping=True)
+    return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+
+# Debugging: Print the type and content of the first example
+print("Type of dataset['test']:", type(dataset['test']))
+print("Type of the first element in dataset['test']:", type(dataset['test'][0]))
+print("Content of the first element in dataset['test']:", dataset['test'][0])
+
+# Test the model on a few examples
+for example in dataset['test'][:5]:
+    try:
+        # If the example is a string, then it's likely that 'dataset['test']' is not loaded as expected
+        if isinstance(example, str):
+            print(f"Article: {example}\n")
+            print(f"Summary: {summarize(example)}\n")
+        else:
+            # Access the 'article' field if the example is a dictionary
+            article = example.get('article', None)
+            if article:
+                print(f"Article: {article}\n")
+                print(f"Summary: {summarize(article)}\n")
+            else:
+                print("No 'article' field found in this example.")
+    except Exception as e:
+        print(f"Error processing example: {e}")