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

Create modelfiles that use api LLMs, e.g. gpt-4 #2314

Closed
mdillondc opened this issue May 16, 2024 · 2 comments
Closed

Create modelfiles that use api LLMs, e.g. gpt-4 #2314

mdillondc opened this issue May 16, 2024 · 2 comments

Comments

@mdillondc
Copy link

Is your feature request related to a problem? Please describe.
I tried creating a modelfile with FROM gpt-4 but despite being able to select and use that model because I have my API key set up, saving the model file results in "pull model manifest: file does not exist".

Describe the solution you'd like
Modelfiles should be able to utilize models connected though an API, such as those from OpenAI.

Describe alternatives you've considered
Using prompts after selecting a gpt model, but that is not ideal.

Additional context
None.

@SchneiderSam
Copy link

same here +1

@tjbck
Copy link
Contributor

tjbck commented May 16, 2024

Duplicate #665, For anyone who might come across this in the future, please refrain from creating duplicate issues. It only slows me down from getting the actual work done for these features to get implemented. @mdillondc @SchneiderSam If you see any duplicate requests by other users please refer them to #665, Thanks in advance!

@tjbck tjbck closed this as completed May 16, 2024
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

3 participants