mmBERT-base-msa-32768 / tokenizer_config.json
de-francophones's picture
Upload Malay pruned model
5072e16 verified
Raw
History Blame Contribute Delete
380 Bytes
{
"backend": "tokenizers",
"bos_token": "<bos>",
"cls_token": "<bos>",
"eos_token": "<eos>",
"mask_token": "<mask>",
"model_max_length": 8192,
"pad_token": "<pad>",
"padding_side": "right",
"sep_token": "<eos>",
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>",
"model_input_names": [
"input_ids",
"attention_mask"
]
}