metadata
license: apache-2.0
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
license: apache-2.0
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