GPT-2 124M checkpoint pre-trained on OpenWebText 27.5B tokens(github.com)

1 pointsby megadragon9vor 26 Tagen1 comments

https://github.com/workofart/ml-by-hand/releases/tag/gpt2-124m-openwebtext-56000

1 comments

megadragon9vor 26 Tagen

Model built and trained using a hand-built deep learning library (numpy primitives)