kw_pubmed_1000_0.000006 / tokenizer_config.json
enoriega's picture
Training in progress, step 4
162d47e
raw
history blame contribute delete
388 Bytes
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}