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

feat: add Mistral Instruct model to the catalog #1773

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

jeffmaury
Copy link
Contributor

Fixes #1771

What does this PR do?

Add a new model to the catalog

Screenshot / video of UI

N/A

What issues does this PR fix or reference?

#1771

How to test this PR?

Test with playground

Fixes containers#1771

Signed-off-by: Jeff MAURY <jmaury@redhat.com>
@@ -303,6 +303,19 @@
},
"sha256": "893ae2442b36b2e8e1134ccbf8c0d9bd670648d0964509202ab30c9cbb3d2114",
"backend": "none"
},
{
"id": "hf.MaziyarPanahi.Mistral-7B-Instruct-v0.3.Q4_K_M",
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

should it come from https://huggingface.co/mistralai rather than "hf.MaziyarPanahi"

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

They don't provide GGUF files thus this repo

Copy link
Collaborator

@benoitf benoitf left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I don't know if we have a process to say if we include or not a model like if we can trust the author or not, if there are no changes from the original model etc but it's a different story.

Copy link
Contributor

@axel7083 axel7083 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

I know we had some idea at some point to include the model converter (.safetensor => gguf) inside ai lab

Maybe we should re-evaluate this ?

@jeffmaury
Copy link
Contributor Author

LGTM

I know we had some idea at some point to include the model converter (.safetensor => gguf) inside ai lab

* [Integrate Model converter for running models without GGUF file #542](https://github.com/containers/podman-desktop-extension-ai-lab/issues/542)

* https://github.com/containers/ai-lab-recipes/tree/main/convert_models

Maybe we should re-evaluate this ?

That needs to be tested first as GGUF contains model metadata (template,...) that are not present in the safe tensor format

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

Successfully merging this pull request may close these issues.

Add Mistral Instruct model to the catalog
4 participants