CoolFace
Modelpublic

WpythonW/RUbert-tiny_custom_test

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes17downloads
tokenizer_config.json65 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    "1": {12      "content": "[UNK]",13      "lstrip": false,14      "normalized": false,15      "rstrip": false,16      "single_word": false,17      "special": true18    },19    "2": {20      "content": "[CLS]",21      "lstrip": false,22      "normalized": false,23      "rstrip": false,24      "single_word": false,25      "special": true26    },27    "3": {28      "content": "[SEP]",29      "lstrip": false,30      "normalized": false,31      "rstrip": false,32      "single_word": false,33      "special": true34    },35    "4": {36      "content": "[MASK]",37      "lstrip": false,38      "normalized": false,39      "rstrip": false,40      "single_word": false,41      "special": true42    }43  },44  "clean_up_tokenization_spaces": true,45  "cls_token": "[CLS]",46  "do_basic_tokenize": true,47  "do_lower_case": false,48  "mask_token": "[MASK]",49  "max_length": 512,50  "model_max_length": 2048,51  "never_split": null,52  "pad_to_multiple_of": null,53  "pad_token": "[PAD]",54  "pad_token_type_id": 0,55  "padding_side": "right",56  "sep_token": "[SEP]",57  "stride": 0,58  "strip_accents": null,59  "tokenize_chinese_chars": true,60  "tokenizer_class": "BertTokenizer",61  "truncation_side": "right",62  "truncation_strategy": "longest_first",63  "unk_token": "[UNK]"64}65