GPT-2 については、下記記事が一番分かりやすいと思う。
gpt2-xl-japanese | https://huggingface.co/nlp-waseda/gpt2-xl-japanese | This is Japanese GPT2 with approximately 1.5B parameters pretrained on Japanese Wikipedia and CC-100 The model architecture of the model are based on Radford+ 2019. |
---|