Can we fine-tune a ChatGPT model that is accessible via ChatCompletion?

March 22, 2023

I have fine-tuned an openai language model (curie) and was able to access the model via openai.Completion.create method but I could not access the fine-tuned model via openai.ChatCompletion.create.

By researching a bit I have found out that the problem is not in the fine-tuning but in the fact that the original curie model is not accessible via openai.ChatCompletion.create.

By looping over these models:

models = ['gpt-3.5-turbo', 'davinci', 'curie', 'babbage', 'ada']

I found out that only gpt-3.5-turbo model is accessible via openai.ChatCompletion.create and it is not accessible via openai.Completion.create. In contrast, the remaining four models are accessible via openai.Completion.create but are not accessible via openai.ChatCompletion.create.

So, my first question if someone can confirm my finding? Is what I found out written somewhere on openai documentation pages?

My second question is if it is possible to fine-tune a model that supports Chat / Dialogue?

For example on the official page I see that:

Fine-tuning is currently only available for the following base models:
davinci, curie, babbage, and ada.

So, did I get it right that we can only fine-tune models that do not support Chat / Dialogue?

>Solution :

Q1:

I found out that only gpt-3.5-turbo model is accessible via
openai.ChatCompletion.create and it is not accessible via
openai.Completion.create. In contrast, the remaining four models are
accessible via openai.Completion.create but are not accessible via
openai.ChatCompletion.create.

So, my first question if someone can confirm my finding?

A1:

Yes, correct. The reason why this is the case is that the gpt-3.5.-turbo model is a GPT-3.5 model. All the other models you mentioned (i.e., davinci, curie, babbage, and ada) are GPT-3 models.

GPT-3.5 models use a different API endpoint than GPT-3 models. This is not explicitly written in the documentation, but it’s very clear if you read the whole documentation.

Q2: