|
{ |
|
"add_prefix_space": 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 |
|
}, |
|
"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 |
|
}, |
|
"model_max_length": 512, |
|
"name_or_path": "../models/codeT5Tokenizer", |
|
"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": "/work2/06922/jiyang/maverick2/.cache/5941df5e4315c5ab63b7b2ac791fb0bf0f209744a055c06b43b5274849137cdd.b9905d0575bde443a20834122b6e2d48e853b2e36444ce98ddeb43c38097eb3f", |
|
"tokenizer_class": "RobertaTokenizer", |
|
"tokenizer_file": null, |
|
"unk_token": { |
|
"__type": "AddedToken", |
|
"content": "<unk>", |
|
"lstrip": false, |
|
"normalized": true, |
|
"rstrip": false, |
|
"single_word": false |
|
} |
|
} |
|
|