Skip to content

Add RecurseChat Local App #691

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

Merged
merged 2 commits into from
Jun 7, 2024
Merged

Conversation

xyc
Copy link
Contributor

@xyc xyc commented May 21, 2024

Hi HF team!

Super cool idea to use local model directly from HuggingFace. I'm hoping to add RecurseChat (a local first AI app) to "Use this model" list in this PR. Still in the process of adding deeplink functionality (mainly trying to automatically figuring out a chat template, and need to release it on the Mac App Store), but want to get some feedback first.

The deep link roughly works like below:

add-hf-gguf.mp4

If you need to test the app, please feel free to shoot an email to [email protected] for a TestFlight invite. Thank you for considering the request.

@coyotte508 coyotte508 changed the title Add RecurseChat Add RecurseChat Local App May 21, 2024
@julien-c
Copy link
Member

@xyc UX looks good!

I've installed the app on my mac.

Are you considering doing a free tier or free version of RecurseChat so users of the Hub can try it easily?

@xyc
Copy link
Contributor Author

xyc commented May 22, 2024

@julien-c Thanks! Happy to think of ways to make it easier for HF users to try. We are considering doing free trials via TestFlight. Will have an update about this in a day or two.

@xyc
Copy link
Contributor Author

xyc commented May 24, 2024

We added free trials for Hugging Face users here (Edit: We have made free trials available on the front page) using "Sign in with Hugging Face" and TestFlight. Here is a demo:

hf-trial.mov

Also, shipped HF model and deep link support in RecurseChat v1.0.119. (url for testing: recursechat://new-hf-gguf-model?hf-model-id=QuantFactory/Meta-Llama-3-8B-Instruct-GGUF). This library helps a lot in getting the right GGUF metadata to apply a proper chat template! Here is how it looks like:

hf-custom-url.mov

Anything else we could do to help get this through? Thank you for the consideration.

mainTask: "text-generation",
macOSOnly: true,
displayOnModelPage: isGgufModel,
deeplink: (model) => new URL(`recursechat://new-hf-gguf-model?hf-model-id=${model.id}`),
Copy link
Member

Choose a reason for hiding this comment

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

btw take a look at #738 in case you'd like to support opening from an optional specific file inside the repo! thanks!

Copy link
Contributor Author

Choose a reason for hiding this comment

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

hi @julien-c Thanks for the heads up! We'll look into adding it, but it'll take some time to release it.

I've updated the PR branch. Would it be fine to add this as is and we'll make another PR for file path url later? It would help largely simplify our current users experience to add a model from HF.

@xyc xyc force-pushed the add-recursechat branch from be0e9be to 2ec369d Compare June 6, 2024 18:59
@xyc xyc requested a review from pcuenca as a code owner June 6, 2024 18:59
@krampstudio krampstudio merged commit 7a82e6e into huggingface:main Jun 7, 2024
4 checks passed
@krampstudio
Copy link
Collaborator

@xyc the integration with HF is now live.

@xyc
Copy link
Contributor Author

xyc commented Jun 11, 2024

@krampstudio Awesome! Thank you for the update.

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.

3 participants