Update app.py

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-client = InferenceClient(model="https://zgg3nzdpswxy4a-80.proxy.runpod.net/")
+client = InferenceClient(model="https://zgg3nzdpswxy4a-80.proxy.runpod.net")
 
 def inference(message):
     partial_message = ""
-    for token in client.text_generation(message, max_new_tokens=256, stream=True):
+    for token in client.text_generation(message, max_new_tokens=128, stream=True):
         partial_message += token
         yield partial_message