tokenizer_config.json

{"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": null, "additional_special_tokens": ["[QUESTION]"], "model_max_length": 512, "special_tokens_map_file": "/gscratch/efml/anasa2/.huggingface/5f4b3317a7019c90796012c43a7d4e3db0b5c0a50445a053279b5f058f7b1d7b.5f8d8adb4106c43ee43d2bbbdf22053095b63cf98e866c0164335424931f338c", "name_or_path": "tau/splinter-large-qass", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "SplinterTokenizer"}