Update app.py

app.py

@@ -1,24 +1,41 @@
 import gradio as gr
 from transformers import GPT2LMHeadModel, GPT2Tokenizer
+import torch
 
-# Load GPT-2 large model and tokenizer
-model_name = "openai-community/gpt2-large"  # Using the gpt2-large variant
-model = GPT2LMHeadModel.from_pretrained(model_name)
+# Load model and tokenizer
+model_name = "openai-community/gpt2-large"
 tokenizer = GPT2Tokenizer.from_pretrained(model_name)
+model = GPT2LMHeadModel.from_pretrained(model_name)
+
+# Set padding token (GPT-2 doesn't have one by default)
+tokenizer.pad_token = tokenizer.eos_token
+model.config.pad_token_id = model.config.eos_token_id
 
-# Function to generate responses from GPT-2
+# Chat function
 def chat_with_gpt2(user_input):
-    # Encode the user input and append to the model's context
-    inputs = tokenizer.encode(user_input, return_tensors="pt")
-    # Generate a response from GPT-2
-    outputs = model.generate(inputs, max_length=1000, num_return_sequences=1, no_repeat_ngram_size=2, pad_token_id=50256)
+    # Encode input
+    inputs = tokenizer.encode(user_input, return_tensors="pt", truncation=True, max_length=512)
     
-    # Decode and return the response
+    # Generate response (limit output for speed and memory)
+    outputs = model.generate(
+        inputs,
+        max_length=250,  # shortened for performance
+        num_return_sequences=1,
+        do_sample=True,
+        temperature=0.7,
+        top_k=50,
+        top_p=0.95,
+        pad_token_id=tokenizer.eos_token_id
+    )
+    
+    # Decode response
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return response
-
-# Create the Gradio interface
-interface = gr.Interface(fn=chat_with_gpt2, inputs="text", outputs="text", title="Trip Planner Chatbot")
+    
+    # Return only the bot's reply (not repeating input)
+    return response[len(user_input):].strip()
 
-# Launch the interface
-interface.launch()
+# Gradio UI
+interface = gr.Interface(
+    fn=chat_with_gpt2,
+    inputs=gr.Textbox(lines=3, placeholder="Ask me about your trip..."),
+    outputs="