sumitdotml
/

moe-emergence

Text Generation

mixture-of-experts

expert-specialization

Model card Files Files and versions

moe-emergence / README.md

Commit History

updated model card with ablation results and all 4 runs

4049aa7

sumit commited on 26 days ago

add dense and moe checkpoints

3ff42e6

sumitdotml commited on 27 days ago