CoolFace
Modelpublic

WariHima/hourai3-90m-base-ja-v1

sourceHugging Facecc-by-sa-4.0updated 2mo agoView on Hugging Face
0likes5downloads
Model Card

蓬莱3 90m base ja v1

architecture:
  • —lfm2moe
tarined by:
  • —rtx3060 * 40m training code in ./training_codes

tokenizer from ku-nlp/gpt2-small-japanese-char +(qwne3 chat format | special tokens)

dataset:
  • —OmniAICreator/Japanese-Wikipedia-202506 use 30k rows 2 epoch