A PEER model (implementation of the paper https://arxiv.org/abs/2407.04153 ).

2B model made of 256x256 experts.

Training & inference code available at: https://github.com/ThomasVuNguyen/PEER

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support