GLuCoSE-base-ja-v2 / tokenizer_config.json
yano0's picture
Add new SentenceTransformer model.
8791d08 verified
{
"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
},
"32769": {
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32770": {
"content": "<ent>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"32771": {
"content": "<ent2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<ent>",
"<ent2>",
"<ent>",
"<ent2>",
"<ent>",
"<ent2>",
"<ent>",
"<ent2>",
"<ent>",
"<ent2>",
"<ent>",
"<ent2>",
"<ent>",
"<ent2>",
"<ent>",
"<ent2>",
"<ent>",
"<ent2>"
],
"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,
"special": false
},
"entity_token_2": {
"__type": "AddedToken",
"content": "<ent2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": false
},
"entity_unk_token": "[UNK]",
"eos_token": "</s>",
"mask_token": "<mask>",
"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",
"unk_token": "<unk>"
}