Update app.py

app.py

@@ -1,3 +1,4 @@
+import streamlit as st
 from transformers import GPT2Tokenizer, GPT2LMHeadModel
 
 # Initialize the tokenizer and model
@@ -5,24 +6,32 @@ model_name = 'gpt2-large'
 tokenizer = GPT2Tokenizer.from_pretrained(model_name)
 model = GPT2LMHeadModel.from_pretrained(model_name)
 
+# Set the title for the Streamlit app
+st.title("GPT-2 Blog Post Generator")
+
 # Text input for the user
-text = "my cat"
+text = st.text_area("Enter your Topic: ")
+
+if text:
+    try:
+        # Encode input text
+        encoded_input = tokenizer(text, return_tensors='pt')
 
-# Encode input text
-encoded_input = tokenizer(text, return_tensors='pt', padding=True, truncation=True)
+        # Generate text
+        output = model.generate(
+            input_ids=encoded_input['input_ids'],
+            max_length=200,  # Adjust length as needed
+            num_return_sequences=1,
+            no_repeat_ngram_size=2,
+            top_p=0.95,
+            top_k=50
+        )
 
-# Generate text
-output = model.generate(
-    input_ids=encoded_input['input_ids'],
-    attention_mask=encoded_input['attention_mask'],
-    max_length=200,  # Adjust length as needed
-    num_return_sequences=1,
-    no_repeat_ngram_size=2,
-    top_p=0.95,
-    top_k=50,
-    pad_token_id=tokenizer.eos_token_id  # Set pad_token_id to eos_token_id
-)
+        # Decode generated text
+        generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
 
-# Decode generated text
-generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
-generated_text
+        # Display the generated text
+        st.subheader("Generated Blog Post")
+        st.write(generated_text)
+    except Exception as e:
+        st.error(f"An error occurred: {e}")