[X] I used the GitHub search to look for a similar issue and didn't find it.
[X] I searched the Marvin documentation for this feature.
Describe the current behavior
When using new model, marvin fails.
openai.error.InvalidRequestError: This is not a chat model and thus not supported in the v1/chat/completions endpoint. Did you mean to use v1/completions?
First check
Describe the current behavior
When using new model, marvin fails.
Describe the proposed behavior
Use marvin with gpt-3.5-turbo-instruct.
Example Use
No response
Additional context
No response