Update app.py

app.py

@@ -26,7 +26,7 @@ def load_model():
 model, tokenizer = load_model()
 
 @spaces.GPU(duration=80)  # Added the decorator here
-def generate_response(prompt, max_length=2048):
+def generate_response(prompt, max_length=1024):
     inputs = tokenizer(prompt, return_tensors="pt").to("cuda" if torch.cuda.is_available() else "cpu")
     outputs = model.generate(**inputs, max_length=max_length)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)