Hugging Face's logo

WariHima
/
hourai3-7m-base-ja

Safetensors
Japanese
lfm2_moe
Model card Files
xet
 Community

蓬莱3 7m base ja v1

architecture:

  • lfm2moe

tarined by:

  • rtx3060 * 30m
    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
Downloads last month
11
Safetensors
Model size
6.55M params
Tensor type
F32
·
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for WariHima/hourai3-7m-base-ja

Finetunes
1 model

Dataset used to train WariHima/hourai3-7m-base-ja

Collection including WariHima/hourai3-7m-base-ja