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

Use of open-source model #38

Open
Bachstelze opened this issue Apr 7, 2023 · 2 comments
Open

Use of open-source model #38

Bachstelze opened this issue Apr 7, 2023 · 2 comments

Comments

@Bachstelze
Copy link

Is it possible to use LLaMa as vector embeddings?

@BohuTANG
Copy link
Contributor

BohuTANG commented Apr 8, 2023

Sure, But still trying to figure out what the API of LLaMa is, some docs about it?
Now, Databend uses the OpenAI API doc here:

https://platform.openai.com/docs/guides/embeddings/what-are-embeddings

@Bachstelze Bachstelze changed the title Use of LLaMa Use of open-source model Apr 8, 2023
@Bachstelze
Copy link
Author

LLaMA are Open and Efficient Foundation Language Models. Though I think that the decoder architecture isn't suitable for information retrival. Open ai uses probably encoder Models like sentence Bert or sentence similarity Models.

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

2 participants