fix: Set max_new_tokens to 200

app.py

@@ -5,7 +5,7 @@ import gradio as gr
 
 # Use a pipeline as a high-level helper
 from transformers import pipeline
-pipe = pipeline("text-generation", model="NousResearch/Hermes-3-Llama-3.1-8B")
+pipe = pipeline("text-generation", model="NousResearch/Hermes-3-Llama-3.1-8B", max_new_tokens=200)
 
 @spaces.GPU(duration=120)
 def llama3_1_8B(question):