CoolFace
Modelpublic

NeuML/colbert-bert-tiny

sourceHugging Faceapache-2.0updated 1mo agoView on Hugging Face
2likes92kdownloads
tokenizer_config.json75 linesDownload Raw Back to root
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    "100": {12      "content": "[UNK]",13      "lstrip": false,14      "normalized": false,15      "rstrip": false,16      "single_word": false,17      "special": true18    },19    "101": {20      "content": "[CLS]",21      "lstrip": false,22      "normalized": false,23      "rstrip": false,24      "single_word": false,25      "special": true26    },27    "102": {28      "content": "[SEP]",29      "lstrip": false,30      "normalized": false,31      "rstrip": false,32      "single_word": false,33      "special": true34    },35    "103": {36      "content": "[MASK]",37      "lstrip": false,38      "normalized": false,39      "rstrip": false,40      "single_word": false,41      "special": true42    },43    "30522": {44      "content": "[Q] ",45      "lstrip": false,46      "normalized": true,47      "rstrip": false,48      "single_word": false,49      "special": false50    },51    "30523": {52      "content": "[D] ",53      "lstrip": false,54      "normalized": true,55      "rstrip": false,56      "single_word": false,57      "special": false58    }59  },60  "clean_up_tokenization_spaces": true,61  "cls_token": "[CLS]",62  "do_basic_tokenize": true,63  "do_lower_case": true,64  "extra_special_tokens": {},65  "mask_token": "[MASK]",66  "model_max_length": 1000000000000000019884624838656,67  "never_split": null,68  "pad_token": "[MASK]",69  "sep_token": "[SEP]",70  "strip_accents": null,71  "tokenize_chinese_chars": true,72  "tokenizer_class": "BertTokenizer",73  "unk_token": "[UNK]"74}75