CoolFace
Modelpublic

CloneBO/CloneLM-Heavy

sourceHugging Faceupdated 2y agoView on Hugging Face
1likes5.7kdownloads
tokenizer.json179 linesDownload Raw Back to root
1{2  "version": "1.0",3  "truncation": null,4  "padding": null,5  "added_tokens": [6    {7      "id": 0,8      "content": "[PAD]",9      "single_word": false,10      "lstrip": false,11      "rstrip": false,12      "normalized": false,13      "special": true14    },15    {16      "id": 1,17      "content": "[UNK]",18      "single_word": false,19      "lstrip": false,20      "rstrip": false,21      "normalized": false,22      "special": true23    },24    {25      "id": 2,26      "content": "[CLS]",27      "single_word": false,28      "lstrip": false,29      "rstrip": false,30      "normalized": false,31      "special": true32    },33    {34      "id": 3,35      "content": "[SEP]",36      "single_word": false,37      "lstrip": false,38      "rstrip": false,39      "normalized": false,40      "special": true41    },42    {43      "id": 4,44      "content": "[MASK]",45      "single_word": false,46      "lstrip": false,47      "rstrip": false,48      "normalized": false,49      "special": true50    }51  ],52  "normalizer": {53    "type": "BertNormalizer",54    "clean_text": true,55    "handle_chinese_chars": true,56    "strip_accents": null,57    "lowercase": false58  },59  "pre_tokenizer": {60    "type": "BertPreTokenizer"61  },62  "post_processor": {63    "type": "TemplateProcessing",64    "single": [65      {66        "SpecialToken": {67          "id": "[CLS]",68          "type_id": 069        }70      },71      {72        "Sequence": {73          "id": "A",74          "type_id": 075        }76      },77      {78        "SpecialToken": {79          "id": "[SEP]",80          "type_id": 081        }82      }83    ],84    "pair": [85      {86        "SpecialToken": {87          "id": "[CLS]",88          "type_id": 089        }90      },91      {92        "Sequence": {93          "id": "A",94          "type_id": 095        }96      },97      {98        "SpecialToken": {99          "id": "[SEP]",100          "type_id": 0101        }102      },103      {104        "Sequence": {105          "id": "B",106          "type_id": 1107        }108      },109      {110        "SpecialToken": {111          "id": "[SEP]",112          "type_id": 1113        }114      }115    ],116    "special_tokens": {117      "[CLS]": {118        "id": "[CLS]",119        "ids": [120          2121        ],122        "tokens": [123          "[CLS]"124        ]125      },126      "[SEP]": {127        "id": "[SEP]",128        "ids": [129          3130        ],131        "tokens": [132          "[SEP]"133        ]134      }135    }136  },137  "decoder": {138    "type": "WordPiece",139    "prefix": "##",140    "cleanup": true141  },142  "model": {143    "type": "WordPiece",144    "unk_token": "[UNK]",145    "continuing_subword_prefix": "##",146    "max_input_chars_per_word": 100,147    "vocab": {148      "[PAD]": 0,149      "[UNK]": 1,150      "[CLS]": 2,151      "[SEP]": 3,152      "[MASK]": 4,153      "A": 5,154      "C": 6,155      "D": 7,156      "E": 8,157      "F": 9,158      "G": 10,159      "H": 11,160      "I": 12,161      "K": 13,162      "L": 14,163      "M": 15,164      "N": 16,165      "P": 17,166      "Q": 18,167      "R": 19,168      "S": 20,169      "T": 21,170      "V": 22,171      "W": 23,172      "Y": 24,173      "-": 25,174      "[ClSep]": 26,175      "[AbHC]": 27,176      "[AbLC]": 28177    }178  }179}