[Bug]: How to use Local downloaded Hugging face model

[mustangs0786]

What happened?

Hi team,

i have downloaded phi model from hugging face in my local folder, now i want to pass the local path and use that to call LLM, i don't want to hit hugging face again..

how to do that

import os
from litellm import completion

messages = [{ "content": "There's a llama in my garden 😱 What should I do?","role": "user"}]

response = completion(
model="huggingface/Users/rahul/Qwen2.5-3B-Instruct",
messages=[{ "content": "Hello, how are you?","role": "user"}],
stream=True
)
print(response)

i am getting error here.. please anyone help......

Relevant log output

No response

Are you a ML Ops Team?

No

What LiteLLM version are you on ?

latest

Twitter / LinkedIn details

No response