Update app.py

app.py

@@ -133,7 +133,7 @@ if user_input:
     if torch.cuda.is_available():
         inputs = {k: v.to('cuda') for k, v in inputs.items()}
 
-    outputs = model.generate(**inputs, max_length=500, do_sample=True, temperature=0.7, pad_token_id=tokenizer.eos_token_id)
+    outputs = model.generate(**inputs, max_length=5000, do_sample=True, temperature=0.7, pad_token_id=tokenizer.eos_token_id)
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     reply = response[len(input_text):].strip()