Hello!

I've been in the lab synthesizing captions, with my trusty sidekick Blip, and along the way I had an interesting idea. I thought of designing an incredibly simple model that accepts simple instruction pairs, adjective noun pairs specifically, and outputs 2d vertices.

The current implementation has been implemented by myself then ran over with Claude, not because I am incompetent, but because I recognize tools written by experts may have more technique than my newbie self.

As with all projects, this will be updated with proportion to the feedback received, if someone's using it and wants to keep using it, i'm happy to keep working on anything. Thanks, all! 🤗

-<3

https://colab.research.google.com/gist/SMeyersMrOvkill/8d4686db803f6c5f43fafc1c94b1c8c6/polypathdelement.ipynb

reacted to whitphx's post with 🔥 7 months ago

Post

2362

Have you looked at the Gemini Nano local LLM?
Gradio-Lite, the in-browser ver. of Gradio, gives it a rich interface using only Python code, even for such an in-browser AI app!

Try out a chat app that runs completely inside your browser 👇
https://www.gradio.app/playground?demo=Hello_World&code=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

Note: Gemini Nano is currently only available on Chrome Canary, and you need to opt-in.
Follow the "Installation" section in https://huggingface.co/blog/Xenova/run-gemini-nano-in-your-browser .

updated 2 Spaces 7 months ago

Static

🌐

Identify objects in your uploaded image

Mod

🖼

New activity in openskyml/models about 1 year ago

Upload y2mate.com - Helmet Blacktop 1994.mp3

#1 opened about 1 year ago by

soleofsoul