BERT-whitening-pytorch:Pytorch版本的BERT白化-源码

上传者: 42126274 | 上传时间: 2021-08-17 15:06:24 | 文件大小: 24.01MB | 文件类型: ZIP
BERT增白 这是“美化的Pytorch实施。 BERT增白在文本语义搜索中非常实用,其中增白操作不仅提高了无监督语义矢量匹配的性能,而且减小了矢量维,有利于减少内存使用量,提高矢量搜索引擎的检索效率,例如,FAISS。 这种方法最早是由苏建林在他的博客中提出的 。 重现实验结果 准备 下载数据集: $ cd data/ $ ./download_datasets.sh $ cd ../ 下载型号: $ cd model/ $ ./download_models.sh $ cd ../ 下载数据集和模型文件后, data/和model/目录如下: ├── data │ ├── AllNLI.tsv │ ├── download_datasets.sh │ └── downstream │ ├── COCO │ ├── CR │

文件下载

资源详情

[{"title":"( 35 个子文件 24.01MB ) BERT-whitening-pytorch:Pytorch版本的BERT白化-源码","children":[{"title":"BERT-whitening-pytorch-main","children":[{"title":"run_example.py <span style='color:#111;'> 5.68KB </span>","children":null,"spread":false},{"title":"model","children":[{"title":"download_models.sh <span style='color:#111;'> 1.07KB </span>","children":null,"spread":false}],"spread":true},{"title":"run.sh <span style='color:#111;'> 361B </span>","children":null,"spread":false},{"title":"all_utils.py <span style='color:#111;'> 2.90KB </span>","children":null,"spread":false},{"title":"eval_with_whitening(nli).py <span style='color:#111;'> 4.67KB </span>","children":null,"spread":false},{"title":"whiten","children":[{"title":"bert-large-uncased-first_last_avg-whiten(NLI).pkl <span style='color:#111;'> 8.00MB </span>","children":null,"spread":false},{"title":"bert-base-nli-mean-tokens-first_last_avg-whiten(NLI).pkl <span style='color:#111;'> 4.50MB </span>","children":null,"spread":false},{"title":"bert-large-nli-mean-tokens-first_last_avg-whiten(NLI).pkl <span style='color:#111;'> 8.00MB </span>","children":null,"spread":false},{"title":"bert-base-uncased-first_last_avg-whiten(NLI).pkl <span style='color:#111;'> 4.50MB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 4.14KB </span>","children":null,"spread":false},{"title":"eval_with_whitening(target).py <span style='color:#111;'> 3.61KB </span>","children":null,"spread":false},{"title":"senteval","children":[{"title":"mrpc.py <span style='color:#111;'> 4.10KB </span>","children":null,"spread":false},{"title":"engine.py <span style='color:#111;'> 6.22KB </span>","children":null,"spread":false},{"title":"sick.py <span style='color:#111;'> 11.78KB </span>","children":null,"spread":false},{"title":"trec.py <span style='color:#111;'> 3.48KB </span>","children":null,"spread":false},{"title":"sst.py <span style='color:#111;'> 3.85KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 2.65KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 264B </span>","children":null,"spread":false},{"title":"rank.py <span style='color:#111;'> 4.53KB </span>","children":null,"spread":false},{"title":"tools","children":[{"title":"ranking.py <span style='color:#111;'> 14.92KB </span>","children":null,"spread":false},{"title":"classifier.py <span style='color:#111;'> 7.56KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"relatedness.py <span style='color:#111;'> 4.43KB </span>","children":null,"spread":false},{"title":"validation.py <span style='color:#111;'> 10.12KB </span>","children":null,"spread":false}],"spread":false},{"title":"binary.py <span style='color:#111;'> 3.63KB </span>","children":null,"spread":false},{"title":"probing.py <span style='color:#111;'> 6.63KB </span>","children":null,"spread":false},{"title":"snli.py <span style='color:#111;'> 4.47KB </span>","children":null,"spread":false},{"title":"sts.py <span style='color:#111;'> 7.63KB </span>","children":null,"spread":false}],"spread":false},{"title":"data","children":[{"title":"downstream","children":[{"title":"get_transfer_data.bash <span style='color:#111;'> 8.16KB </span>","children":null,"spread":false},{"title":"tokenizer.sed <span style='color:#111;'> 2.14KB </span>","children":null,"spread":false}],"spread":true},{"title":"download_datasets.sh <span style='color:#111;'> 181B </span>","children":null,"spread":false}],"spread":true},{"title":"train_whiten(nli).py <span style='color:#111;'> 2.18KB </span>","children":null,"spread":false},{"title":"eval_without_whitening.py <span style='color:#111;'> 3.30KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.24KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明