Bug: sometimes return error `Command evaluate_code returned: Error: The model: gpt-4 does not exist` when execute with --gpt3only prefix

[saccohuo]

Bug: sometimes return error Command evaluate_code returned: Error: The model: gpt-4 does not exist when execute with --gpt3only prefix

[Mars-e]

https://github.com/Torantulino/Auto-GPT/issues/187#issuecomment-1496599571

Thanks to this kind reference, please edit the .env file accordingly.

This is also my walkaround to use only gpt3, and works.

#SMART_LLM_MODEL="gpt-4" SMART_LLM_MODEL="gpt-3.5-turbo"

I hope this helps. Please give us feedback!

[bensig]

I have edited my SMART_LLM_MODEL in .env and it is not working... still get the same error.

[rajeshalda]

same error ..

[Pwuts]

Duplicate of #168