wmt14-de-en-20k-unigram / special_tokens_map.json
speedcell4's picture
Upload tokenizer
5e6beb0 verified
raw
history blame contribute delete
734 Bytes
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"cls_token": "<s>",
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "<unk>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"sep_token": "</s>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}