Update app.py

app.py

@@ -33,7 +33,7 @@ examples=[
 
 
 # Stream text - stream tokens with InferenceClient from TGI
-async def predict(message, chatbot, system_prompt="", temperature=0.1, max_new_tokens=4096, repetition_penalty=1.1,):
+async def predict(message, chatbot, system_prompt="", temperature=0.1, max_new_tokens=4096, top_p=0.6, repetition_penalty=1.1,):
     
     if system_prompt != "":
         input_prompt = f"<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n "
@@ -64,7 +64,7 @@ async def predict(message, chatbot, system_prompt="", temperature=0.1, max_new_t
         
 
 # No Stream - batch produce tokens using TGI inference endpoint
-def predict_batch(message, chatbot, system_prompt="", temperature=0.1, max_new_tokens=4096, repetition_penalty=1.1):
+def predict_batch(message, chatbot, system_prompt="", temperature=0.1, max_new_tokens=4096, top_p=0.6, repetition_penalty=1.1):
     
     if system_prompt != "":
         input_prompt = f"<s>[INST] <<SYS>>\n{system_prompt}\n<</SYS>>\n\n "