feedback_patients / tokenizer.json
genie10's picture
Upload 7 files
6b85a11 verified
raw
history blame
357 Bytes
{
"tokenizer_class": "XLMRobertaTokenizerFast",
"model": {
"type": "SentencePiece",
"model_file": "sentencepiece.bpe.model"
},
"vocab_size": 250002,
"bos_token": "<s>",
"eos_token": "</s>",
"unk_token": "<unk>",
"pad_token": "<pad>",
"mask_token": "<mask>",
"padding_side": "right",
"truncation_side": "right"
}