IdiomBERT-system-e / tokenizer_config.json
Justarandomperson's picture
Add IdiomBERT joint mBERT EN+ES+HI+TE (backbone + task heads)
bc4a94e verified
Raw
History Blame Contribute Delete
459 Bytes
{
"backend": "tokenizers",
"cls_token": "[CLS]",
"do_lower_case": false,
"is_local": true,
"local_files_only": false,
"mask_token": "[MASK]",
"max_length": 128,
"model_max_length": 512,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"stride": 0,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}