thainer-corpus-v2-base-model / tokenizer_config.json
wannaphong's picture
Upload tokenizer
13ff667
raw
history blame contribute delete
550 Bytes
{
"additional_special_tokens": [
"<s>NOTUSED",
"</s>NOTUSED",
"<_>"
],
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": null,
"tokenizer_class": "CamembertTokenizer",
"unk_token": "<unk>"
}