Code Monkey home page Code Monkey logo

cedille-ai's People

Contributors

mar-muel avatar masterscrat avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Forkers

redchew-fork mght marcuschasse fredatgithub ireneik alexandrearduino edenweb1 ay0tgourmetart phoenixdigitalfx aicodehunt likhonwtf m4ldoror

cedille-ai's Issues

Transformers integration and hosting the model on Huggingface hub 🤗

Hey @MasterScrat !

Great work and the demo UI is so beautiful 😍 !

Would be really cool to have this model on the huggingface hub! I see you currently save your model checkpoints through google storage. Would you be interested in sharing the model in the Hugging Face Hub?

This integration would allow anyone from the community to easily download and use the model from the Hub.
We can help you set up a cedille-ai organization. You can create an org here.

The GPT-J architecture is already available in Transformers in PyTorch. And this script can be used to convert the jax checkpoint to pt.

Once you have the weights in PT it should be fairly easy to push the model on the hub.

from transformers import GPTJForCausalLM

model = GPTJForCausalLM.from_pretrained("path_to_converted_ckpt")
model.push_to_hub("boris-6b", organization="cedille-ai")

then users can simply use it using

model = GPTJForCausalLM.from_pretrained("cedille-ai/boris-6b")

Manually creating the repos and adding new models should also be a relatively straightforward process if you've used Git before. This is a step-by-step guide explaining the process in case you're interested. Please let us know if you would be interested and if you have any questions. Thank you!

(cc @LysandreJik)

Inference on GPU

Is inference on a GPU feasible? If so, how much GPU memory would be needed? (16GB is apparently not enough)

Or is there a distilled or lighter-weight version?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.