tokenizer_config.json

{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "x_sep_token": "[X_SEP]", "pad_token": "[PAD]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": "/gscratch/efml/anasa2/.huggingface/73e9134d07adccf5cf38d24c2f241f87e3febd91b209b279fff2741c9ff2ab4f.6fa7d8b91dc65e73f96549c829087df43aa7359e1d576908a012e7747d67c6c2", "name_or_path": "microsoft/prophetnet-large-uncased", "tokenizer_class": "ProphetNetTokenizer"}