Sasando-1-7M / tokenizer_config.json
afrizalha's picture
Upload tokenizer
29474a7 verified
raw
history blame
1.49 kB
{
"added_tokens_decoder": {
"0": {
"content": "<BOS>",
"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
},
"3": {
"content": "<SEP>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "<PAD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<CLS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<MASK>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<BOS>",
"clean_up_tokenization_spaces": true,
"cls_token": "<CLS>",
"eos_token": "<EOS>",
"mask_token": "<MASK>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<PAD>",
"sep_token": "<SEP>",
"tokenizer_class": "PreTrainedTokenizerFast"
}