fix: llm_provider add openai finetune compatibility

[Undertone0809]

llm_provider add openai finetune compatibility.

A error happens in #617

original code:

from litellm import completion

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

print(response.choices[0].message)

after:

from litellm import completion

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)

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
litellm	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	Oct 16, 2023 10:48am

[ishaan-jaff]

LGTM !

[ishaan-jaff]

Thanks for this awesome PR @Undertone0809 !

We'd love to give you a shoutout for your work ! What's your linkedin / twitter ?