Closed bfirsh closed 3 years ago
Hi @bfirsh, thank you very much for your kind update! I looked at Replicate, it is a very good place to make reproducible machine learning models and I am also excited to share our project with other people there. I will be merging your pull and any further updates are welcome! Thanks again!
I am so glad to hear it is helpful. 😄
Here's a link to claim your page if you want to edit it. You can change the description, add examples, and stuff. We'll also feature it on our explore page and twitter account.
Also if you want to follow our work or help out making models reproducible, we've got a Discord chatroom where we hang out: https://discord.gg/QmzJApGjyE
Hey @jiupinjia! 👋
This pull request makes it possible to run your model inside a Docker environment, which makes it easier for other people to run it. We're using an open source tool called Cog that handles all the complex stuff like
Dockerfile
, CUDA configuration, etc.You can run commands inside the Docker environment:
Or, a prediction:
This also means we can make a web page where other people can try out your model! View it here: https://replicate.ai/jiupinjia/stylized-neural-painting-oil
A bit like the Runway page you already have, but you have to sign in to run models on Runway now. If you claim your page by signing in with GitHub, then we'll feature it on our site and tweet about it.
In case you're wondering who I am, I'm from Replicate, where we're trying to make machine learning reproducible. We got frustrated that we couldn't run all the really interesting ML work being done. So, we're going round implementing models we like. 😊