Fill-Mask
Transformers
Safetensors
English
modernbert
trimmed
ModernBERT-large-16384 / tokenizer_config.json
lbourdois's picture
Upload English pruned model
22f90cb verified
Raw
History Blame Contribute Delete
21.8 kB
{
"added_tokens_decoder": {
"0": {
"content": "|||IP_ADDRESS|||",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"1": {
"content": "<|padding|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16270": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16271": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16272": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16273": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16274": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16275": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16276": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16277": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16278": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16279": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16280": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16281": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16282": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16283": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16284": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16285": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16286": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16287": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16288": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16289": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16290": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16291": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16292": {
"content": " ",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16293": {
"content": "|||EMAIL_ADDRESS|||",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16294": {
"content": "|||PHONE_NUMBER|||",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16295": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16296": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16297": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16298": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16299": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16300": {
"content": "[MASK]",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"16301": {
"content": "[unused0]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16302": {
"content": "[unused1]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16303": {
"content": "[unused2]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16304": {
"content": "[unused3]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16305": {
"content": "[unused4]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16306": {
"content": "[unused5]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16307": {
"content": "[unused6]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16308": {
"content": "[unused7]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16309": {
"content": "[unused8]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16310": {
"content": "[unused9]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16311": {
"content": "[unused10]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16312": {
"content": "[unused11]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16313": {
"content": "[unused12]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16314": {
"content": "[unused13]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16315": {
"content": "[unused14]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16316": {
"content": "[unused15]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16317": {
"content": "[unused16]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16318": {
"content": "[unused17]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16319": {
"content": "[unused18]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16320": {
"content": "[unused19]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16321": {
"content": "[unused20]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16322": {
"content": "[unused21]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16323": {
"content": "[unused22]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16324": {
"content": "[unused23]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16325": {
"content": "[unused24]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16326": {
"content": "[unused25]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16327": {
"content": "[unused26]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16328": {
"content": "[unused27]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16329": {
"content": "[unused28]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16330": {
"content": "[unused29]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16331": {
"content": "[unused30]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16332": {
"content": "[unused31]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16333": {
"content": "[unused32]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16334": {
"content": "[unused33]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16335": {
"content": "[unused34]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16336": {
"content": "[unused35]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16337": {
"content": "[unused36]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16338": {
"content": "[unused37]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16339": {
"content": "[unused38]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16340": {
"content": "[unused39]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16341": {
"content": "[unused40]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16342": {
"content": "[unused41]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16343": {
"content": "[unused42]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16344": {
"content": "[unused43]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16345": {
"content": "[unused44]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16346": {
"content": "[unused45]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16347": {
"content": "[unused46]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16348": {
"content": "[unused47]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16349": {
"content": "[unused48]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16350": {
"content": "[unused49]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16351": {
"content": "[unused50]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16352": {
"content": "[unused51]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16353": {
"content": "[unused52]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16354": {
"content": "[unused53]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16355": {
"content": "[unused54]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16356": {
"content": "[unused55]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16357": {
"content": "[unused56]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16358": {
"content": "[unused57]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16359": {
"content": "[unused58]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16360": {
"content": "[unused59]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16361": {
"content": "[unused60]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16362": {
"content": "[unused61]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16363": {
"content": "[unused62]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16364": {
"content": "[unused63]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16365": {
"content": "[unused64]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16366": {
"content": "[unused65]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16367": {
"content": "[unused66]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16368": {
"content": "[unused67]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16369": {
"content": "[unused68]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16370": {
"content": "[unused69]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16371": {
"content": "[unused70]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16372": {
"content": "[unused71]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16373": {
"content": "[unused72]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16374": {
"content": "[unused73]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16375": {
"content": "[unused74]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16376": {
"content": "[unused75]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16377": {
"content": "[unused76]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16378": {
"content": "[unused77]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16379": {
"content": "[unused78]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16380": {
"content": "[unused79]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16381": {
"content": "[unused80]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16382": {
"content": "[unused81]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"16383": {
"content": "[unused82]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
}
},
"clean_up_tokenization_spaces": true,
"unk_token": "[UNK]",
"sep_token": "[SEP]",
"pad_token": "[PAD]",
"cls_token": "[CLS]",
"mask_token": "[MASK]",
"bos_token": "[CLS]",
"eos_token": "[SEP]",
"model_max_length": 8192,
"tokenizer_class": "PreTrainedTokenizerFast",
"model_input_names": [
"input_ids",
"attention_mask"
]
}