mt5_empty2_5k_msp / tokenizer_config.json
Kajiura Teruno
Deleted 2,500 words from duplicated vocabulary
84e7c73
{
"additional_special_tokens": [],
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 0,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "<unk>"
}