xzyao's picture
add tokenizer
6a4066b
raw
history blame
548 Bytes
{
"bos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}