Sindhi-DistilmBERT-MultiTask / tokenizer_config.json
Kashif786's picture
Multi-Task Model: SentencePiece + Scaled Gold Corpus (NER F1: 0.79)
9ecd23a verified
Raw History Blame Contribute Delete
490 Bytes
{
"backend": "tokenizers",
"cls_token": "[CLS]",
"is_local": false,
"local_files_only": false,
"mask_token": "[MASK]",
"max_length": 128,
"model_max_length": 1000000000000000019884624838656,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "[SEP]",
"stride": 0,
"tokenizer_class": "TokenizersBackend",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}