OmniAlign / tokenizer_config.json
WPS-Qingqiu's picture
Upload folder using huggingface_hub
5e173be verified
Raw
History Blame Contribute Delete
10 kB
{
"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": "<ʘ‿ʘ>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250003": {
"content": "<╯°□°)╯︵ ┻━┻>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250004": {
"content": "<◕_◕>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250005": {
"content": "<ಠ_ಠ>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250006": {
"content": "<(`^´)>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250007": {
"content": "<¯\\_(ツ)_/¯>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250008": {
"content": "<(✧ω✧)>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250009": {
"content": "<(◍•ᴗ•◍)>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250010": {
"content": "<(≧▽≦)>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250011": {
"content": "<(๑•̀ㅂ•́)و✧>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250012": {
"content": "<(。◕‿◕。)>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250013": {
"content": "<(•̀ᴗ•́)و>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250014": {
"content": "<(>_<)>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250015": {
"content": "<(。•́︿•̀。)>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250016": {
"content": "<(≧∇≦)ノ>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250017": {
"content": "<(๑˃̵ᴗ˂̵)و>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250018": {
"content": "<(≧∇≦)ノ♪>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250019": {
"content": "<(。・ω・。)ノ♬>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250020": {
"content": "<(•̀⌄•́)>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250021": {
"content": "<(。•́︿•̀。)ノ>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250022": {
"content": "<(。・ω・。)ノ♡>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250023": {
"content": "<(๑•́ ₃ •̀๑)>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250024": {
"content": "<(≧∇≦)ノ☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250025": {
"content": "<(。・ω・。)ノ☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250026": {
"content": "<(。•́︿•̀。)ノ☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250027": {
"content": "<(。•́︿•̀。)ノ♪>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250028": {
"content": "<(。•́︿•̀。)ノ♡>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250029": {
"content": "<(。•́︿•̀。)ノ☆♪>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250030": {
"content": "<(。•́︿•̀。)ノ♡♪>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250031": {
"content": "<(。•́︿•̀。)ノ☆♡>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250032": {
"content": "<(。•́︿•̀。)ノ☆♡♪>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250033": {
"content": "<(。•́︿•̀。)ノ♪♡>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250034": {
"content": "<(。•́︿•̀。)ノ♪☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250035": {
"content": "<(。•́︿•̀。)ノ♪☆♡>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250036": {
"content": "<(。•́︿•̀。)ノ♪♡☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250037": {
"content": "<(。•́︿•̀。)ノ♡☆♪>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250038": {
"content": "<(。•́︿•̀。)ノ♡♪☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250039": {
"content": "<(。•́︿•̀。)ノ☆♪♡>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250040": {
"content": "<(。•́︿•̀。)ノ♪♡☆111>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250041": {
"content": "<(11。•́︿•̀。)ノ♪♡☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250042": {
"content": "<12(。•́︿•̀。)ノ♪♡☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250043": {
"content": "<123(。•́︿•̀。)ノ♪♡☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250044": {
"content": "<(。•́︿23•̀。)ノ♪♡☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250045": {
"content": "<(1321。•́︿•̀。)ノ♪♡☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250046": {
"content": "<(123335。•́︿•̀。)ノ♪♡☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250047": {
"content": "<123(123335。•́︿•̀。)ノ♪♡☆>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"extra_special_tokens": {},
"mask_token": "<mask>",
"model_max_length": 8192,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "XLMRobertaTokenizerFast",
"unk_token": "<unk>"
}