acmc's picture
Pushing tokenizer (#2)
6587cdb
{
"additional_special_tokens": [
"<s>",
"</s>",
"<unk>",
"[SEP]",
"<pad>",
"[CLS]",
"[MASK]",
"[CONTENT]",
"[SUMMARY]",
"[BACKGROUND]",
"[METHODS]",
"[RESULTS]",
"[CONCLUSIONS]",
" | ",
" ||| "
],
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": {
"content": "[CLS]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "[MASK]",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token": {
"content": "[SEP]",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}