Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

The model: gpt-4 does not exist #71

Closed
dudelama opened this issue Apr 3, 2023 · 15 comments
Closed

The model: gpt-4 does not exist #71

dudelama opened this issue Apr 3, 2023 · 15 comments

Comments

@dudelama
Copy link

dudelama commented Apr 3, 2023

I get the following error:

File "C:\Users\PranavTej\AppData\Local\Packages\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\LocalCache\local-packages\Python311\site-packages\openai\api_requestor.py", line 679, in _interpret_response_line
raise self.handle_error_response(
openai.error.InvalidRequestError: The model: gpt-4 does not exist

@engma-linguistics
Copy link

You have to have API access to it specifically, otherwise you probably ought replace any gpt-4 call with gpt-3.5-turbo. It's way cheaper anyways!

@dudelama
Copy link
Author

dudelama commented Apr 3, 2023

where do i do it, where to make the update to gpt-3.5-turbo?

@Torantulino
Copy link
Member

Give me 5 mins.

@Torantulino
Copy link
Member

Fixed! 51e293f

Now use the argument

--gpt3only

To run AutoGPT without GPT4 access!

@n2nco
Copy link

n2nco commented Apr 3, 2023

If you're not an insider or openai sycophant, you've got to pay for early openai api access (plugins or gpt-4)

@rogeriosmorais
Copy link

rogeriosmorais commented Apr 3, 2023

I have the API key, have inserted it into my .env file and I still get this error. I tried both with and without quotes surrounding it. "Last used" on my OpenAI keys page says "Never".

In fact, even if I provide the --gpt3only argument, I still get this error message.

@slavakurilyak
Copy link
Contributor

slavakurilyak commented Apr 4, 2023

I'm also seeing the same error, despite the new "GPT3.5 Only Mode".

Note, scripts/token_counter.py uses hard-coded values for model. Maybe update all model mentions using environment variables: SMART_LLM_MODEL and FAST_LLM_MODEL?

@sjnt1
Copy link

sjnt1 commented Apr 11, 2023

Im having this issue alot. Every time it tries to evaluate code it tries to use gpt 4 and the error message.

Does updating the model mentions those enviroment variables fix the issue?

@claytondukes
Copy link

I'm having this issue but have a paid gpt-4 account. I want it to use gpt-4.

@Slowly-Grokking
Copy link
Contributor

I'm having this issue but have a paid gpt-4 account. I want it to use gpt-4.

you have beta access to GPT4 API? ChatGPT Plus for $20/month doesn't work for this right now.

@claytondukes
Copy link

I'm having this issue but have a paid gpt-4 account. I want it to use gpt-4.

you have beta access to GPT4 API? ChatGPT Plus for $20/month doesn't work for this right now.

Not the beta, I have the $20/month one. So I should only use gpt-3 then?

@Slowly-Grokking
Copy link
Contributor

So I should only use gpt-3 then?

yeah, use the --gpt3only

@charltonh
Copy link

I'd rather just use a local copy of gpt4all

@sjnt1
Copy link

sjnt1 commented Apr 14, 2023

What is your experience with gpt4all?

@richbeales
Copy link
Contributor

closing this

Say383 pushed a commit to Say383/Auto-GPT that referenced this issue Sep 8, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests