Certain Large Models Fail

What version of Codex is running?

v0.1.2504161551

Which model were you using?

gpt-3.5-turbo-instruct

What platform is your computer?

Linux 5.15.0-131-generic x86_64 x86_64

What steps can reproduce the bug?

For specific GPT models, such as gpt-3.5-turbo-1106 and gpt-3.5-turbo-instruct-0914, execution is unsuccessful with the following error messages. Other models, like gpt-4, operate normally. Is this a bug in the code, or does the model not support Codex?

!Image

What is the expected behavior?

_No response_

What do you see instead?

_No response_

Additional information

_No response_