luke-japanese-large-finetuned-ner / tokenizer_config.json
Mizuiro-sakura's picture
Upload 11 files
3577ab2
{
"additional_special_tokens": [
{
"__type": "AddedToken",
"content": "<ent>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
{
"__type": "AddedToken",
"content": "<ent2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
{
"__type": "AddedToken",
"content": "<ent>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
{
"__type": "AddedToken",
"content": "<ent2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"entity_mask2_token": "[MASK2]",
"entity_mask_token": "[MASK]",
"entity_pad_token": "[PAD]",
"entity_token_1": {
"__type": "AddedToken",
"content": "<ent>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"entity_token_2": {
"__type": "AddedToken",
"content": "<ent2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"entity_unk_token": "[UNK]",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"max_entity_length": 32,
"max_mention_length": 30,
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"task": null,
"tokenizer_class": "MLukeTokenizer",
"tokenizer_file": "models/luke-japanese-large/hf_luke_japanese_epoch20/tokenizer.json",
"unk_token": "<unk>"
}