cotet5_small_fix / tokenizer_config.json
SaulLu's picture
complete vocab
b77236c
{
"errors": "replace",
"unk_token": {
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"bos_token": {
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"eos_token": {
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"add_prefix_space": false,
"sep_token": {
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"cls_token": {
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"pad_token": {
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"mask_token": {
"content": "<mask>",
"single_word": false,
"lstrip": true,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"model_max_length": 512,
"tokenizer_class": "RobertaTokenizer"
}