japanese-soseki-gpt2-1b / tokenizer.json /tokenizer_config.json
jweb's picture
second commit
101d6a0
raw
history blame contribute delete
455 Bytes
{
"additional_special_tokens": [],
"bos_token": "<s>",
"cls_token": "[CLS]",
"do_lower_case": false,
"eos_token": "</s>",
"extra_ids": 0,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"special_tokens_map_file": "/home/mycat/model/rinna/rinna-gpt/special_tokens_map.json",
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}