seq2tag-grammar / tokenizer_config.json
lenguist's picture
Training in progress, epoch 1
b70bbd0
raw
history blame contribute delete
579 Bytes
{
"bos_token": "<s>",
"cls_token": "<s>",
"eos_token": "</s>",
"extra_ids": 0,
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"name_or_path": "ukr-models/xlm-roberta-base-uk",
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"special_tokens_map_file": "./xlm-roberta-base-uk/special_tokens_map.json",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}