CoolFace
Modelpublic

flexitok/mod-tokenizers-zero-padded-rtl_4digit

sourceHugging Facemitupdated 7mo agoView on Hugging Face
0likes16downloads
tokenizer_config.json74 linesDownload Raw Back to root
1{2  "added_tokens_decoder": {3    "0": {4      "content": "<unk>",5      "lstrip": false,6      "normalized": false,7      "rstrip": false,8      "single_word": false,9      "special": true10    },11    "1": {12      "content": "<s>",13      "lstrip": false,14      "normalized": false,15      "rstrip": false,16      "single_word": false,17      "special": true18    },19    "2": {20      "content": "</s>",21      "lstrip": false,22      "normalized": false,23      "rstrip": false,24      "single_word": false,25      "special": true26    },27    "3": {28      "content": "<pad>",29      "lstrip": false,30      "normalized": false,31      "rstrip": false,32      "single_word": false,33      "special": true34    },35    "4": {36      "content": "mod",37      "lstrip": false,38      "normalized": false,39      "rstrip": false,40      "single_word": false,41      "special": true42    },43    "5": {44      "content": "=",45      "lstrip": false,46      "normalized": false,47      "rstrip": false,48      "single_word": false,49      "special": true50    },51    "6": {52      "content": " ",53      "lstrip": false,54      "normalized": false,55      "rstrip": false,56      "single_word": false,57      "special": true58    }59  },60  "additional_special_tokens": [61    "mod",62    "=",63    " "64  ],65  "bos_token": "<s>",66  "clean_up_tokenization_spaces": false,67  "eos_token": "</s>",68  "extra_special_tokens": {},69  "model_max_length": 1000000000000000019884624838656,70  "pad_token": "<pad>",71  "tokenizer_class": "PreTrainedTokenizerFast",72  "unk_token": "<unk>",73  "number_handling": "rtl_4digit"74}