[Bug]: recognizing openai finetune model as huggingface model when calling

[Undertone0809]

What happened?

A bug happened!

I would like to use openai finetune model but failed. It recognizes finetune model as huggingface model.

from dotenv import load_dotenv
from litellm import completion

load_dotenv()


response = completion(
  model="ft:gpt-3.5-turbo-0613:xxx::xxx",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ]
)

print(response.choices[0].message)

docs: https://docs.litellm.ai/docs/tutorials/finetuned_chat_gpt

Relevant log output

Provider List: https://docs.litellm.ai/docs/providers


Give Feedback / Get Help: https://github.com/BerriAI/litellm/issues/new
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.

Traceback (most recent call last):
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\site-packages\litellm\main.py", line 260, in completion
    model, custom_llm_provider, dynamic_api_key = get_llm_provider(model=model, custom_llm_provider=custom_llm_provider, api_base=api_base)
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\site-packages\litellm\utils.py", line 1485, in get_llm_provider
    raise e
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\site-packages\litellm\utils.py", line 1482, in get_llm_provider
    raise ValueError(f"LLM Provider NOT provided. Pass in the LLM provider you are trying to call. E.g. For 'Huggingface' inference endpoints pass in `completion(model='huggingface/{model}',..)` Learn more: https://docs.litellm.ai/docs/providers")
ValueError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. E.g. For 'Huggingface' inference endpoints pass in `completion(model='huggingface/ft:gpt-3.5-turbo-0613:xxx::xxx',..)` Learn more: https://docs.litellm.ai/docs/providers

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "E:\project_hub\babel\babel_gpt35_finetune\babel_finetune\alpha\demo3.py", line 13, in <module>
    response = completion(
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\site-packages\litellm\utils.py", line 791, in wrapper
    raise e
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\site-packages\litellm\utils.py", line 750, in wrapper
    result = original_function(*args, **kwargs)
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\site-packages\litellm\timeout.py", line 53, in wrapper
    result = future.result(timeout=local_timeout_duration)
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\concurrent\futures\_base.py", line 458, in result
    return self.__get_result()
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\concurrent\futures\_base.py", line 403, in __get_result
    raise self._exception
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\site-packages\litellm\timeout.py", line 42, in async_func
    return func(*args, **kwargs)
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\site-packages\litellm\main.py", line 1188, in completion
    raise exception_type(
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\site-packages\litellm\utils.py", line 3000, in exception_type
    raise e
  File "E:\Programming\anaconda\envs\babel_gpt35_finetune\lib\site-packages\litellm\utils.py", line 2982, in exception_type
    raise APIError(status_code=500, message=str(original_exception), llm_provider=custom_llm_provider, model=model)
litellm.exceptions.APIError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. E.g. For 'Huggingface' inference endpoints pass in `completion(model='huggingface/ft:gpt-3.5-turbo-0613:xxx::xxx',..)` Learn more: https://docs.litellm.ai/docs/providers

### Twitter / LinkedIn details

_No response_

[Undertone0809]

I have solve this problem when I add parameter custom_llm_provider=openai. But I don't know the detail reason why I should add this provider. It seem openai finetune model can not find a llm_provider when calling get_llm_provider()

[krrishdholakia]

@Undertone0809 i see the PR you made is merged, i'll update this ticket once it's in prod (we need to fix some linting issues on our end)

[ishaan-jaff]

this is done