gal_enptsp_mBERT / tokenizer_config.json
mbruton's picture
Upload 11 files
773e537
raw
history blame contribute delete
498 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-enpt_mbert-base/snapshots/d30fb1ab00f5aff867da3dbf5a6bf380f82aad71/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}