Update app.py

app.py

@@ -118,6 +118,7 @@ def hermes_generate_response(msg_prompt: str) -> dict:
     Returns:
         dict: A dictionary containing the user's message prompt and the model's response.
     """
+    generation_params = {"do_sample": True,"temperature": 0.7,"top_p": 0.95,"top_k": 40,"max_new_tokens": 512,"repetition_penalty": 1.1}
     pipe = pipeline("text-generation",model=model, tokenizer=tokenizer, **generation_params)
     try:
         prompt_template=f'''<|im_start|>system