XLM-R_WOR / tokenizer_config.json
contactsharma's picture
uploaded model
ade0436 verified
{
"added_tokens_decoder": {
"0": {
"content": "<s>",
"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": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250001": {
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250002": {
"content": "🦬",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250003": {
"content": "🤠",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250004": {
"content": "🧐",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250005": {
"content": "👽",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250006": {
"content": "🫂",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250007": {
"content": "🐟",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250008": {
"content": "🫶",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250009": {
"content": "🥃",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250010": {
"content": "🤯",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250011": {
"content": "🔪",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250012": {
"content": "🐖",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250013": {
"content": "🐈",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250014": {
"content": "🥁",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250015": {
"content": "🥚",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250016": {
"content": "🤍",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250017": {
"content": "⁉",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250018": {
"content": "🤢",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250019": {
"content": "🐕",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250020": {
"content": "👹",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250021": {
"content": "🔨",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250022": {
"content": "🔯",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250023": {
"content": "🧘",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250024": {
"content": "🦰",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250025": {
"content": "🎻",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250026": {
"content": "🐗",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250027": {
"content": "🤬",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250028": {
"content": "💨",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250029": {
"content": "🐏",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250030": {
"content": "🥲",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250031": {
"content": "🪓",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250032": {
"content": "🍛",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250033": {
"content": "🥶",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250034": {
"content": "👺",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250035": {
"content": "🐅",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250036": {
"content": "🦚",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250037": {
"content": "🍵",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250038": {
"content": "🥳",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250039": {
"content": "🤫",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250040": {
"content": "🥛",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250041": {
"content": "🐓",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250042": {
"content": "🦓",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250043": {
"content": "⚖",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250044": {
"content": "⛪",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250045": {
"content": "🛕",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250046": {
"content": "🫢",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250047": {
"content": "🕍",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250048": {
"content": "🤮",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250049": {
"content": "🃏",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250050": {
"content": "🛐",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250051": {
"content": "🍗",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250052": {
"content": "🙉",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250053": {
"content": "🎏",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250054": {
"content": "🥵",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250055": {
"content": "🏺",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250056": {
"content": "🫡",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250057": {
"content": "🥱",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250058": {
"content": "🏰",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250059": {
"content": "🚒",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250060": {
"content": "‼",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250061": {
"content": "⛏",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250062": {
"content": "🥺",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250063": {
"content": "🐑",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250064": {
"content": "🤰",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250065": {
"content": "🤚",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250066": {
"content": "🖕",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250067": {
"content": "🤐",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250068": {
"content": "🐔",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250069": {
"content": "🗡",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250070": {
"content": "😧",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250071": {
"content": "✝",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250072": {
"content": "🕎",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250073": {
"content": "🍱",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250074": {
"content": "🏅",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250075": {
"content": "🌚",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250076": {
"content": "🤜",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250077": {
"content": "🦾",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250078": {
"content": "💺",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"250079": {
"content": "🕴",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": "<mask>",
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}