tokenizer_config.json

{"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": "data/s2orc_with_specter_without_scidocs/specter/corpus_seed_0/seed_0_ep5knn20-25_en3random_without_knn_hn2knn3998-4000/model_BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext", "do_basic_tokenize": true, "never_split": null}