kaist-ai/langbridge_encoder_tokenizer

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": "</s>",13      "lstrip": false,14      "normalized": false,15      "rstrip": false,16      "single_word": false,17      "special": true18    },19    "2": {20      "content": "<unk>",21      "lstrip": false,22      "normalized": false,23      "rstrip": false,24      "single_word": false,25      "special": true26    },27    "250100": {28      "content": "\f",29      "lstrip": false,30      "normalized": false,31      "rstrip": false,32      "single_word": false,33      "special": true34    },35    "250101": {36      "content": "    ",37      "lstrip": false,38      "normalized": false,39      "rstrip": false,40      "single_word": false,41      "special": true42    },43    "250102": {44      "content": "   ",45      "lstrip": false,46      "normalized": false,47      "rstrip": false,48      "single_word": false,49      "special": true50    },51    "250103": {52      "content": "\r",53      "lstrip": false,54      "normalized": false,55      "rstrip": false,56      "single_word": false,57      "special": true58    },59    "250104": {60      "content": "\t",61      "lstrip": false,62      "normalized": false,63      "rstrip": false,64      "single_word": false,65      "special": true66    },67    "250105": {68      "content": "\n",69      "lstrip": false,70      "normalized": false,71      "rstrip": false,72      "single_word": false,73      "special": true74    },75    "250106": {76      "content": "  ",77      "lstrip": false,78      "normalized": false,79      "rstrip": false,80      "single_word": false,81      "special": true82    },83    "250107": {84      "content": "\u000b",85      "lstrip": false,86      "normalized": false,87      "rstrip": false,88      "single_word": false,89      "special": true90    }91  },92  "additional_special_tokens": [93    "\f",94    "    ",95    "   ",96    "\r",97    "\t",98    "\n",99    "  ",100    "\u000b"101  ],102  "clean_up_tokenization_spaces": true,103  "eos_token": "</s>",104  "extra_ids": 0,105  "legacy": true,106  "model_max_length": 1000000000000000019884624838656,107  "pad_token": "<pad>",108  "sp_model_kwargs": {},109  "tokenizer_class": "T5Tokenizer",110  "unk_token": "<unk>"111}112