BERT_full-6_tokenized / tokenizer_config.json
Mozart-coder's picture
Upload tokenizer
f21bd4d
{
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": false,
"mask_token": "[MASK]",
"max_len": 512,
"name_or_path": "armheb/DNA_bert_6",
"never_split": null,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--armheb--DNA_bert_6/snapshots/a79a8fd96ad172f964a4dbef3f4d7545a5034baa/special_tokens_map.json",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}