mpnet_pretrain_27 / tokenizer_config.json
onlydj96's picture
add tokenizer
55977bc
{
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"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
},
"name_or_path": "onlydj96/mpnet_pretrain_100",
"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
},
"special_tokens_map_file": "/root/.cache/huggingface/transformers/4aa599e6ac8f0263a04a4569ddadb35dafe43bfb10448da4035dd12101ec111a.1b83d0d7f4d455d37c683966d465a99be7f33983cf93b19ad8d2d23d044ea57a",
"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
}
}