lexdec-medium-char / tokenizer_config.json
bbunzeck's picture
Upload 11 files
cb9c915 verified
{
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "0",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"3": {
"content": "1",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"4": {
"content": "2",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"5": {
"content": "3",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"6": {
"content": "4",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"7": {
"content": "5",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"8": {
"content": "6",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"9": {
"content": "7",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"10": {
"content": "8",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"11": {
"content": "9",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"12": {
"content": "a",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"13": {
"content": "b",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"14": {
"content": "c",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"15": {
"content": "d",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16": {
"content": "e",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"17": {
"content": "f",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"18": {
"content": "g",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"19": {
"content": "h",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"20": {
"content": "i",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"21": {
"content": "j",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"22": {
"content": "k",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"23": {
"content": "l",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"24": {
"content": "m",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"25": {
"content": "n",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"26": {
"content": "o",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"27": {
"content": "p",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"28": {
"content": "q",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"29": {
"content": "r",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"30": {
"content": "s",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"31": {
"content": "t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"32": {
"content": "u",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"33": {
"content": "v",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"34": {
"content": "w",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"35": {
"content": "x",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"36": {
"content": "y",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"37": {
"content": "z",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"38": {
"content": "A",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"39": {
"content": "B",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"40": {
"content": "C",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"41": {
"content": "D",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"42": {
"content": "E",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"43": {
"content": "F",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"44": {
"content": "G",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"45": {
"content": "H",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"46": {
"content": "I",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"47": {
"content": "J",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"48": {
"content": "K",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"49": {
"content": "L",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"50": {
"content": "M",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"51": {
"content": "N",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"52": {
"content": "O",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"53": {
"content": "P",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"54": {
"content": "Q",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"55": {
"content": "R",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"56": {
"content": "S",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"57": {
"content": "T",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"58": {
"content": "U",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"59": {
"content": "V",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"60": {
"content": "W",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"61": {
"content": "X",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"62": {
"content": "Y",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"63": {
"content": "Z",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"64": {
"content": "!",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"65": {
"content": "\"",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"66": {
"content": "#",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"67": {
"content": "$",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"68": {
"content": "%",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"69": {
"content": "&",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"70": {
"content": "'",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"71": {
"content": "(",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"72": {
"content": ")",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"73": {
"content": "*",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"74": {
"content": "+",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"75": {
"content": ",",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"76": {
"content": "-",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"77": {
"content": ".",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"78": {
"content": "/",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"79": {
"content": ":",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"80": {
"content": ";",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"81": {
"content": "<",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"82": {
"content": "=",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"83": {
"content": ">",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"84": {
"content": "?",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"85": {
"content": "@",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"86": {
"content": "[",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"87": {
"content": "\\",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"88": {
"content": "]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"89": {
"content": "^",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"90": {
"content": "_",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"91": {
"content": "`",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"92": {
"content": "{",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"93": {
"content": "|",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"94": {
"content": "}",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"95": {
"content": "~",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"96": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"97": {
"content": "\t",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"98": {
"content": "\n",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"99": {
"content": "\r",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"100": {
"content": "\u000b",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"101": {
"content": "\f",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|endoftext|>",
"tokenizer_class": "PreTrainedTokenizerFast"
}