japanese-mistral-300m-base / tokenizer_config.json
ce-lery's picture
feat: pretrained by recipe v0.1.0
c783850
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 0,
"legacy": true,
"model_max_length": 50000,
"pad_token": "[PAD]",
"sp_model_kwargs": {},
"tokenizer_class": "T5Tokenizer",
"unk_token": "[UNK]"
}