CoolFace
Modelpublic

Mian1234/Finetune_Model

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes6downloads
tokenizer.json203 linesDownload Raw Back to root
1{2  "version": "1.0",3  "truncation": {4    "direction": "Right",5    "max_length": 512,6    "strategy": "LongestFirst",7    "stride": 08  },9  "padding": {10    "strategy": "BatchLongest",11    "direction": "Right",12    "pad_to_multiple_of": null,13    "pad_id": 0,14    "pad_type_id": 0,15    "pad_token": "[PAD]"16  },17  "added_tokens": [18    {19      "id": 0,20      "content": "[PAD]",21      "single_word": false,22      "lstrip": false,23      "rstrip": false,24      "normalized": false,25      "special": true26    },27    {28      "id": 1,29      "content": "[UNK]",30      "single_word": false,31      "lstrip": false,32      "rstrip": false,33      "normalized": false,34      "special": true35    },36    {37      "id": 2,38      "content": "[CLS]",39      "single_word": false,40      "lstrip": false,41      "rstrip": false,42      "normalized": false,43      "special": true44    },45    {46      "id": 3,47      "content": "[SEP]",48      "single_word": false,49      "lstrip": false,50      "rstrip": false,51      "normalized": false,52      "special": true53    },54    {55      "id": 4,56      "content": "[MASK]",57      "single_word": false,58      "lstrip": false,59      "rstrip": false,60      "normalized": false,61      "special": true62    }63  ],64  "normalizer": {65    "type": "BertNormalizer",66    "clean_text": true,67    "handle_chinese_chars": true,68    "strip_accents": null,69    "lowercase": true70  },71  "pre_tokenizer": {72    "type": "BertPreTokenizer"73  },74  "post_processor": {75    "type": "TemplateProcessing",76    "single": [77      {78        "SpecialToken": {79          "id": "[CLS]",80          "type_id": 081        }82      },83      {84        "Sequence": {85          "id": "A",86          "type_id": 087        }88      },89      {90        "SpecialToken": {91          "id": "[SEP]",92          "type_id": 093        }94      }95    ],96    "pair": [97      {98        "SpecialToken": {99          "id": "[CLS]",100          "type_id": 0101        }102      },103      {104        "Sequence": {105          "id": "A",106          "type_id": 0107        }108      },109      {110        "SpecialToken": {111          "id": "[SEP]",112          "type_id": 0113        }114      },115      {116        "Sequence": {117          "id": "B",118          "type_id": 1119        }120      },121      {122        "SpecialToken": {123          "id": "[SEP]",124          "type_id": 1125        }126      }127    ],128    "special_tokens": {129      "[CLS]": {130        "id": "[CLS]",131        "ids": [132          2133        ],134        "tokens": [135          "[CLS]"136        ]137      },138      "[SEP]": {139        "id": "[SEP]",140        "ids": [141          3142        ],143        "tokens": [144          "[SEP]"145        ]146      }147    }148  },149  "decoder": {150    "type": "WordPiece",151    "prefix": "##",152    "cleanup": true153  },154  "model": {155    "type": "WordPiece",156    "unk_token": "[UNK]",157    "continuing_subword_prefix": "##",158    "max_input_chars_per_word": 100,159    "vocab": {160      "[PAD]": 0,161      "[UNK]": 1,162      "[CLS]": 2,163      "[SEP]": 3,164      "[MASK]": 4,165      "0": 5,166      "1": 6,167      "2": 7,168      "3": 8,169      "4": 9,170      "5": 10,171      "6": 11,172      "7": 12,173      "8": 13,174      "9": 14,175      "a": 15,176      "b": 16,177      "c": 17,178      "d": 18,179      "e": 19,180      "f": 20,181      "g": 21,182      "h": 22,183      "i": 23,184      "j": 24,185      "k": 25,186      "l": 26,187      "m": 27,188      "n": 28,189      "o": 29,190      "p": 30,191      "q": 31,192      "r": 32,193      "s": 33,194      "t": 34,195      "u": 35,196      "v": 36,197      "w": 37,198      "x": 38,199      "y": 39,200      "z": 40201    }202  }203}