Trying to run from local llama.cpp server

[DefamationStation]

Hello

I run a server at http://127.0.0.1:8080/v1

and this is my config

default_model = "Llama-3-8b-Q4_K_S"
system_prompt = ""
message_code_theme = "dracula"

[[models]]
name = "Llama-3-8b-Q4_K_S"
api_base = "http://127.0.0.1:8080/v1"
api_key = "api-key-if-required"

but I am getting this error

[jwinpbe]

I found elsewhere that you need to put openai/ before the name of your model to get litellm to talk to llama.cpp and it worked for me.