nordic-ner / tokenizer_config.json
tollefj's picture
tollefj/nordic-ner
c39cb98 verified
{
"add_prefix_space": true,
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250001": {
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250002": {
"content": "<start>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"250003": {
"content": "<end>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"entity_max_length": 8,
"eos_token": "</s>",
"marker_max_length": 128,
"mask_token": "<mask>",
"model_max_length": 256,
"pad_token": "<pad>",
"sep_token": "</s>",
"tokenizer_class": "XLMRobertaTokenizer",
"unk_token": "<unk>"
}