Safetensors
Japanese
lfm2_moe

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
Downloads last month
19
Safetensors
Model size
84.9M 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/hourai3-90m-base-ja-v1

Finetunes
5 models

Dataset used to train WariHima/hourai3-90m-base-ja-v1

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