gal_pt_mBERT / tokenizer_config.json
mbruton's picture
Upload 11 files
17bb1ad
raw
history blame contribute delete
496 Bytes
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"model_max_length": 512,
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--liaad--srl-en_mbert-base/snapshots/0c963b783ca3a81aafce1c53c0bb17715a7f0903/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}