CoolFace
Modelpublic

CAMeL-Lab/readability-arabertv02-word-CE

sourceHugging Facemitupdated 1y agoView on Hugging Face
1likes174downloads
tokenizer_config.json91 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    "5": {44      "content": "[رابط]",45      "lstrip": false,46      "normalized": true,47      "rstrip": false,48      "single_word": true,49      "special": true50    },51    "6": {52      "content": "[بريد]",53      "lstrip": false,54      "normalized": true,55      "rstrip": false,56      "single_word": true,57      "special": true58    },59    "7": {60      "content": "[مستخدم]",61      "lstrip": false,62      "normalized": true,63      "rstrip": false,64      "single_word": true,65      "special": true66    }67  },68  "clean_up_tokenization_spaces": true,69  "cls_token": "[CLS]",70  "do_basic_tokenize": true,71  "do_lower_case": false,72  "mask_token": "[MASK]",73  "max_len": 512,74  "max_length": 512,75  "model_max_length": 512,76  "never_split": [77    "[بريد]",78    "[مستخدم]",79    "[رابط]"80  ],81  "pad_token": "[PAD]",82  "sep_token": "[SEP]",83  "stride": 0,84  "strip_accents": null,85  "tokenize_chinese_chars": true,86  "tokenizer_class": "BertTokenizer",87  "truncation_side": "right",88  "truncation_strategy": "longest_first",89  "unk_token": "[UNK]"90}91