finetuning-hs-model-bert-multilingual / tokenizer_config.json
coderSounak's picture
Training in progress, epoch 1
6f2d3d9
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"model_max_length": 512,
"name_or_path": "QCRI/bert-base-multilingual-cased-pos-english",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--QCRI--bert-base-multilingual-cased-pos-english/snapshots/0b39becb9520965fefc653a7d67dd4accf8cd273/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}