UTR-LM-MLM / tokenizer_config.json
Taykhoom's picture
Upload tokenizer_config.json with huggingface_hub
7681872 verified
{
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"7": {
"content": "<cls>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"8": {
"content": "<mask>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"9": {
"content": "<sep>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": false,
"cls_token": "<cls>",
"eos_token": "<eos>",
"extra_special_tokens": {},
"mask_token": "<mask>",
"model_max_length": 1024,
"pad_token": "<pad>",
"sep_token": "<sep>",
"tokenizer_class": "UtrLmTokenizer",
"unk_token": "<unk>",
"auto_map": {
"AutoTokenizer": [
"tokenization_utrlm.UtrLmTokenizer",
null
]
}
}