Update app.py

app.py

@@ -44,7 +44,7 @@ def respond(
 
     inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
 
-    outputs = model.generate(inputs, max_new_tokens=20)
+    outputs = model.generate(inputs, max_new_tokens=2000)
     gen_text=tokenizer.decode(outputs[0], skip_special_tokens=True)
    
     print(gen_text)