MPNet-still-training / tokenizer_config.json
dev7halo's picture
Upload tokenizer
eb8f29b verified
{
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"cls_token": {
"__type": "AddedToken",
"content": "[CLS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"do_basic_tokenize": true,
"do_lower_case": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"mask_token": {
"__type": "AddedToken",
"content": "[MASK]",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"never_split": null,
"pad_token": {
"__type": "AddedToken",
"content": "[PAD]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token": {
"__type": "AddedToken",
"content": "[SEP]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "MPNetTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "[UNK]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}