BC2GM-Gene-Modified_PubMedBERT / tokenizer_config.json
ghadeermobasher's picture
Training in progress, step 500
c42d2cf
raw
history blame
478 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, "problem_type": "multi_label_classification", "max_length": 512, "model_max_length": 512, "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"}