studio-ousia-luke-base / tokenizer_config.json
daze-unlv's picture
Training in progress, epoch 1
4444c5a verified
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50264": {
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50265": {
"content": "<ent>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"50266": {
"content": "<ent2>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<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": "<ent>",
"entity_token_2": "<ent2>",
"entity_unk_token": "[UNK]",
"eos_token": "</s>",
"errors": "replace",
"mask_token": "<mask>",
"max_entity_length": 32,
"max_mention_length": 30,
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "</s>",
"task": null,
"tokenizer_class": "LukeTokenizer",
"unk_token": "<unk>"
}