Arabic
arabic
tokenizer
morphology
nlp
dialect
df-arc / special_tokens_map.json
fr3on's picture
Upload custom Unigram tokenizer (v1)
ea23987 verified
{
"bos_token": "<s>",
"eos_token": "</s>",
"unk_token": "[UNK]",
"pad_token": "[PAD]",
"cls_token": "[CLS]",
"sep_token": "[SEP]",
"mask_token": "[MASK]"
}