distilHerBERT-base-cased / tokenizer_config.json
BartekK's picture
add tokenizer
61967f9
{
"additional_special_tokens": [],
"bos_token": "<s>",
"cls_token": "<s>",
"do_lowercase_and_remove_accent": false,
"id2lang": null,
"lang2id": null,
"mask_token": "<mask>",
"model_max_length": 512,
"name_or_path": "allegro/herbert-base-cased",
"pad_token": "<pad>",
"sep_token": "</s>",
"special_tokens_map_file": "/home/bartekk/.cache/huggingface/transformers/a77c29d6c21e653166565b0d51ea0a46b918191512e0ae894422060267a0f436.b8e113717eb1828d09e47de853cf49c8fad05ebdce24df2614cd942dc23e2a77",
"tokenizer_class": "HerbertTokenizer",
"unk_token": "<unk>"
}