SloBertAA_Top100_WithOOC_082023 / tokenizer_config.json
gregorgabrovsek's picture
Training in progress, epoch 1
5f0e901
raw
history blame
576 Bytes
{
"additional_special_tokens": [
"<s>NOTUSED",
"</s>NOTUSED"
],
"bos_token": "<s>",
"cls_token": "<s>",
"do_lower_case": false,
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 512,
"name_or_path": "EMBEDDIA/sloberta",
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": null,
"tokenizer_class": "CamembertTokenizer",
"unk_token": "<unk>"
}