climate-news-articles / tokenizer_config.json
pierre-loic's picture
add flauBERT model with undersampling
d6784aa
raw
history blame
539 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_lower_case": false,
"id2lang": null,
"lang2id": null,
"mask_token": "<special1>",
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "FlaubertTokenizer",
"unk_token": "<unk>"
}