mmBERT-base-en-az / tokenizer_config.json
vrashad's picture
Upload mmBERT-base truncated to EN+AZ vocabulary (71K tokens)
b6cfa66 verified
{
"backend": "tokenizers",
"bos_token": "<bos>",
"clean_up_tokenization_spaces": false,
"cls_token": "<bos>",
"eos_token": "<eos>",
"extra_special_tokens": [
"<start_of_turn>",
"<end_of_turn>"
],
"is_local": false,
"mask_token": "<mask>",
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 8192,
"pad_token": "<pad>",
"padding_side": "right",
"sep_token": "<eos>",
"spaces_between_special_tokens": false,
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>"
}