{"description": "GLUE, the General Language Understanding Evaluation benchmark\n(https://gluebenchmark.com/) is a collection of resources for training,\nevaluating, and analyzing natural language understanding systems.\n\n", "citation": "@InProceedings{N18-1101,\n author = \"Williams, Adina\n and Nangia, Nikita\n and Bowman, Samuel\",\n title = \"A Broad-Coverage Challenge Corpus for\n Sentence Understanding through Inference\",\n booktitle = \"Proceedings of the 2018 Conference of\n the North American Chapter of the\n Association for Computational Linguistics:\n Human Language Technologies, Volume 1 (Long\n Papers)\",\n year = \"2018\",\n publisher = \"Association for Computational Linguistics\",\n pages = \"1112--1122\",\n location = \"New Orleans, Louisiana\",\n url = \"http://aclweb.org/anthology/N18-1101\"\n}\n@article{bowman2015large,\n title={A large annotated corpus for learning natural language inference},\n author={Bowman, Samuel R and Angeli, Gabor and Potts, Christopher and Manning, Christopher D},\n journal={arXiv preprint arXiv:1508.05326},\n year={2015}\n}\n@inproceedings{wang2019glue,\n title={{GLUE}: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding},\n author={Wang, Alex and Singh, Amanpreet and Michael, Julian and Hill, Felix and Levy, Omer and Bowman, Samuel R.},\n note={In the Proceedings of ICLR.},\n year={2019}\n}\n", "homepage": "http://www.nyu.edu/projects/bowman/multinli/", "license": "", "features": {"premise": {"dtype": "string", "_type": "Value"}, "hypothesis": {"dtype": "string", "_type": "Value"}, "label": {"names": ["entailment", "neutral", "contradiction"], "_type": "ClassLabel"}, "idx": {"dtype": "int32", "_type": "Value"}}, "builder_name": "glue", "dataset_name": "glue", "config_name": "mnli", "version": {"version_str": "1.0.0", "description": "", "major": 1, "minor": 0, "patch": 0}, "splits": {"train": {"name": "train", "num_bytes": 74619646, "num_examples": 392702, "dataset_name": "glue"}, "validation_matched": {"name": "validation_matched", "num_bytes": 1833783, "num_examples": 9815, "dataset_name": "glue"}, "validation_mismatched": {"name": "validation_mismatched", "num_bytes": 1949231, "num_examples": 9832, "dataset_name": "glue"}, "test_matched": {"name": "test_matched", "num_bytes": 1848654, "num_examples": 9796, "dataset_name": "glue"}, "test_mismatched": {"name": "test_mismatched", "num_bytes": 1950703, "num_examples": 9847, "dataset_name": "glue"}}, "download_checksums": {"https://dl.fbaipublicfiles.com/glue/data/MNLI.zip": {"num_bytes": 312783507, "checksum": null}}, "download_size": 312783507, "dataset_size": 82202017, "size_in_bytes": 394985524}
没有合适的资源?快使用搜索试试~ 我知道了~
huggingface在本地缓存的glue(路径参考:~\.cache\huggingface\datasets\glue)
共11个文件
arrow:9个
json:2个
需积分: 0 21 下载量 171 浏览量
2023-10-09
21:20:28
上传
评论
收藏 17.55MB RAR 举报
温馨提示
在运行TAADPapers的openattack或textattack中可能会用到的文件 ①背景:huggingface连不上 ②解决:主要采取下载到本地的方式运行代码(openattack可以直接改demo里的路径,很方便),有的代码可能不会修改模型和数据集的访问路径(textattack貌似封装的很好,在下找不到文件加载路径~) ③代码请求huggingface之前,会先在缓存文件里寻找,这个压缩文件是我本地缓存的glue,0积分下载,仅供参考~
资源推荐
资源详情
资源评论
收起资源包目录
glue.rar (11个子文件)
glue
cola
1.0.0
dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad
glue-train.arrow 476KB
glue-test.arrow 60KB
dataset_info.json 2KB
glue-validation.arrow 60KB
mnli
1.0.0
dacbe3125aa31d7f70367a07a8a9e72a5a0bfeb5fc42e75c9db75b96da6053ad
glue-validation_matched.arrow 1.75MB
glue-test_matched.arrow 1.77MB
glue-train.arrow 71.29MB
cache-c4fdbbdd8aa58dbb.arrow 7KB
dataset_info.json 3KB
glue-test_mismatched.arrow 1.86MB
glue-validation_mismatched.arrow 1.86MB
共 11 条
- 1
资源评论
卅拓
- 粉丝: 117
- 资源: 4
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功