xlm-mlm-en-2048 / tokenizer_config.json
Xenova's picture
Xenova HF staff
Upload folder using huggingface_hub
e28df6b
raw
history blame contribute delete
550 Bytes
{
"additional_special_tokens": [
"<special0>",
"<special1>",
"<special2>",
"<special3>",
"<special4>",
"<special5>",
"<special6>",
"<special7>",
"<special8>",
"<special9>"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "</s>",
"do_lowercase_and_remove_accent": true,
"id2lang": null,
"lang2id": null,
"mask_token": "<special1>",
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "XLMTokenizer",
"unk_token": "<unk>"
}