Update app.py

app.py

@@ -5,8 +5,8 @@ client = InferenceClient(model="https://9bsneexhe83nu6-80.proxy.runpod.net")
 
 def inference(message, history):
     partial_message = ""
-    for token in client.text_generation(prompt=message, max_new_tokens=1024, stream=True, best_of=1, temperature=0.01, watermark=True, 
-                                        top_p=0.95, do_sample=True, repetition_penalty=0.03):
+    for token in client.text_generation(prompt=message, max_new_tokens=1024, stream=True, best_of=1, temperature=0.1, watermark=True, 
+                                        top_p=0.95, do_sample=True, repetition_penalty=0.1):
         if token.startswith("<s>"):
             return partial_message
         partial_message += token