Remove ` "add_special_tokens"` tokenizer config key

`"add_special_tokens"` now conflicts with a method of the same name in the Transformers library, preventing successful deserialization of the model. The behavior of the model, leading up to the breaking change, was not impacted by this config key.

tokenizer_config.json

@@ -1 +1 @@
-{"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": true, "handle_chinese_chars": true, "lowercase": false, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": "/proj.adsnlp/jupyter-lab/one/fgrezes/astroBERT-Tasks/Task_1_MLM/data/non_ocr_post_1950_xml_tokenizer/BertTokenizerFast/special_tokens_map.json", "name_or_path": "../astroBERT-Tasks/Finetuning_1_NER/trained-models/NER_astroBERT_all_labeled_data_run01/checkpoint-173000/", "add_special_tokens": true, "tokenizer_class": "BertTokenizer"}
+{"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": true, "handle_chinese_chars": true, "lowercase": false, "do_basic_tokenize": true, "never_split": null, "special_tokens_map_file": "/proj.adsnlp/jupyter-lab/one/fgrezes/astroBERT-Tasks/Task_1_MLM/data/non_ocr_post_1950_xml_tokenizer/BertTokenizerFast/special_tokens_map.json", "name_or_path": "../astroBERT-Tasks/Finetuning_1_NER/trained-models/NER_astroBERT_all_labeled_data_run01/checkpoint-173000/", "tokenizer_class": "BertTokenizer"}