{"clean_up_tokenization_spaces": true, "cls_token": "[CLS]", "do_lower_case": false, "mask_token": "[MASK]", "model_max_length": 512, "pad_token": "[PAD]", "sep_token": "[SEP]", "strip_accents": null, "tokenize_chinese_chars": true, "tokenizer_class": "BertTokenizer", "unk_token": "[UNK]", "special_tokens_map_file": "/data1/brandsena/BERT_models/ArchaeoBERT/special_tokens_map.json", "full_tokenizer_file": "/data1/brandsena/BERT_models/ArchaeoBERT/tokenizer.json"} |