wangchan-berta-newmm-tokenizer / tokenizer_config.json
new5558's picture
Upload tokenizer
4415616
raw
history blame contribute delete
495 Bytes
{
"additional_special_tokens": [
"<s>",
"<pad>",
"</s>",
"<unk>",
"<mask>",
"<_>",
"\n"
],
"auto_map": {
"AutoTokenizer": [
"tokenizer.ThaiWordsNewmmTokenizer",
null
]
},
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "ThaiWordsNewmmTokenizer",
"unk_token": "<unk>"
}