luke-base-comp-20201201 / tokenizer_config.json
ryo0634's picture
commit the model and tokenizer.
558a735
raw
history blame
2.51 kB
{
"add_prefix_space": false,
"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": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"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": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"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,
"name_or_path": "huggingface_models/luke-base-comp-20201201",
"pad_token": {
"__type": "AddedToken",
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"special_tokens_map_file": "/home/li0123/.cache/huggingface/transformers/e2adf9c43ab82e2db47210f87bb53aa544055afc59e35389ffff22cd8fbd5d94.0ead83d1c22a0d79f17fc2eb3b32bd99fd9a262049166681d9713840ae868c2a",
"task": null,
"tokenizer_class": "LukeTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}