lightonai/colbertv2.0

1{2  "added_tokens_decoder": {3    "0": {4      "content": "[PAD]",5      "lstrip": false,6      "normalized": false,7      "rstrip": false,8      "single_word": false,9      "special": true10    },11    "1": {12      "content": "[unused0]",13      "lstrip": false,14      "normalized": true,15      "rstrip": false,16      "single_word": false,17      "special": false18    },19    "2": {20      "content": "[unused1]",21      "lstrip": false,22      "normalized": true,23      "rstrip": false,24      "single_word": false,25      "special": false26    },27    "100": {28      "content": "[UNK]",29      "lstrip": false,30      "normalized": false,31      "rstrip": false,32      "single_word": false,33      "special": true34    },35    "101": {36      "content": "[CLS]",37      "lstrip": false,38      "normalized": false,39      "rstrip": false,40      "single_word": false,41      "special": true42    },43    "102": {44      "content": "[SEP]",45      "lstrip": false,46      "normalized": false,47      "rstrip": false,48      "single_word": false,49      "special": true50    },51    "103": {52      "content": "[MASK]",53      "lstrip": false,54      "normalized": false,55      "rstrip": false,56      "single_word": false,57      "special": true58    }59  },60  "clean_up_tokenization_spaces": false,61  "cls_token": "[CLS]",62  "do_lower_case": true,63  "extra_special_tokens": {},64  "mask_token": "[MASK]",65  "model_max_length": 512,66  "pad_token": "[MASK]",67  "sep_token": "[SEP]",68  "strip_accents": null,69  "tokenize_chinese_chars": true,70  "tokenizer_class": "BertTokenizer",71  "unk_token": "[UNK]"72}73