Vbart_Spellcheck-V2 / tokenizer_config.json
Ba2han's picture
Training in progress, step 750
4d72695 verified
raw
history blame
1.17 kB
{
"added_tokens_decoder": {
"0": {
"content": "<PAD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<UNK>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<BOS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<EOS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"32000": {
"content": "<MASK>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<BOS>",
"clean_up_tokenization_spaces": false,
"eos_token": "<EOS>",
"mask_token": "<MASK>",
"model_max_length": 1024,
"pad_token": "<PAD>",
"padding_side": "right",
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"unk_token": "<UNK>"
}