Update app.py

app.py

@@ -17,9 +17,7 @@ hf_hub_download(repo_id=repo_id,
 
 llm = LlamaCpp(
         model_path=model_name,
-        temperature=temperature,
-        max_tokens=2000,
-        top_p=top_p,
+
         callback_manager=callback_manager, 
         verbose=True, # Verbose is required to pass to the callback manager
     )
@@ -46,7 +44,10 @@ def generate(
 
     # stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
     output = ""
-    output=llm(formatted_prompt)
+    output=llm(formatted_prompt,
+               temperature=temperature,
+        max_tokens=30,
+        top_p=top_p,)
     output="ans:"+output
     # for response in stream:
     #     output += response.token.text