updates

app.py

@@ -22,12 +22,13 @@ def generate_response(user_input, chat_history):
     if chat_history:
         prompt = chat_history + prompt
     inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True, max_length=1024)
-    
-    # Move tensors to the same device as model
+
+    # Ensure all tensors are moved to the model's device
     inputs = {k: v.to(model.device) for k, v in inputs.items()}
 
     with torch.no_grad():
-        output = model.generate(**inputs, max_length=512, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
+        # Generate the model's output
+        output = model.generate(**inputs, max_length=1024, num_return_sequences=1, pad_token_id=tokenizer.eos_token_id)
     response = tokenizer.decode(output[0], skip_special_tokens=True)
 
     # Update chat history