my-bigbird-tokenizer_son_v3 / tokenizer_config.json
FiratIsmailoglu's picture
Upload tokenizer
28e37bc verified
{
"added_tokens_decoder": {
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "bigbird_tokenizer_tr.vocab",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32001": {
"content": "[SEP]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32002": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32003": {
"content": "[CLS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32004": {
"content": "[MASK]",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"cls_token": "[CLS]",
"eos_token": "</s>",
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sep_token": "[SEP]",
"sp_model_kwargs": {},
"tokenizer_class": "BigBirdTokenizer",
"unk_token": "bigbird_tokenizer_tr.vocab"
}