Update app.py

app.py

@@ -5,7 +5,7 @@ client = InferenceClient(model="https://zgg3nzdpswxy4a-80.proxy.runpod.net/")
 
 def inference(message, history):
     partial_message = ""
-    for token in client.text_generation(message, max_new_tokens=512, stream=True, temperature=0.5, top_p=0.9):
+    for token in client.text_generation(message, max_new_tokens=128, stream=True, temperature=0.5, top_p=0.9, do_sample=True, decoder_input_details=True):
         partial_message += token
         yield partial_message