llamacpp renamed all commands to have llama- prefix so old code breaks

app.py

@@ -20,7 +20,7 @@ def custom_generate_response_by_api(cust_user_message, prompt_index, prompts_lis
 #Local gguf model using llama.cpp
 def generate_response(user_message): #generate_response_token_by_token
     cmd = [
-        "/app/llama.cpp/main",  # Path to the executable
+        "/app/llama.cpp/llama-cli",  # Path to the executable  #https://github.com/ggerganov/llama.cpp/pull/7809
         "-m", "/app/llama.cpp/models/stablelm-2-zephyr-1_6b-Q4_0.gguf",
         "-p", user_message,
         "-n", "400",