humandna_BERT_1epoch / tokenizer_config.json
simecek's picture
add tokenizer
bfaebcf
raw
history blame contribute delete
533 Bytes
{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "special_tokens_map_file": "/home/jovyan/.cache/huggingface/transformers/e2a020446c0dadc1a84f9fef73389c94f81827af0a86dde4ec17019aec1b7521.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "armheb/DNA_bert_6", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}