{"id":13754244,"url":"https://github.com/xinyi-code/SimCSE-Pytorch","last_synced_at":"2025-05-09T22:31:36.210Z","repository":{"id":45287070,"uuid":"426660595","full_name":"xinyi-code/SimCSE-Pytorch","owner":"xinyi-code","description":"中文数据集下SimCSE+ESimCSE的实现","archived":false,"fork":false,"pushed_at":"2022-05-21T14:52:14.000Z","size":588,"stargazers_count":191,"open_issues_count":12,"forks_count":33,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-04-30T15:24:44.947Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/xinyi-code.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-11-10T14:49:10.000Z","updated_at":"2025-02-06T07:01:22.000Z","dependencies_parsed_at":"2022-08-04T02:30:18.381Z","dependency_job_id":null,"html_url":"https://github.com/xinyi-code/SimCSE-Pytorch","commit_stats":null,"previous_names":["xinyi-code/simcse-pytorch","shuxinyin/simcse-pytorch"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinyi-code%2FSimCSE-Pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinyi-code%2FSimCSE-Pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinyi-code%2FSimCSE-Pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/xinyi-code%2FSimCSE-Pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/xinyi-code","download_url":"https://codeload.github.com/xinyi-code/SimCSE-Pytorch/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253335701,"owners_count":21892714,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-03T09:01:51.768Z","updated_at":"2025-05-09T22:31:33.957Z","avatar_url":"https://github.com/xinyi-code.png","language":"Python","readme":"## SimCSE Inplemention\n\nSimCSE在中文上无监督 + 有监督 pytorch版\n\u003e SimCSE：https://arxiv.org/pdf/2104.08821.pdf   \n\u003e ESimCSE: https://arxiv.org/pdf/2109.04380.pdf\n\n1.database: SNS-B (uploaded)\n\u003e directory: data/SNS-B/  \n\n2.environment\n\u003e torch==1.8.2  \n\u003e transformers==4.12.3\n\u003e \n\u003e video card: 3060Ti 8G    \n\u003e Due to the limitation of the graphics card, the batch_size is set very small.  \n\u003e You can try increasing the batch_size to get better results with video memory allowed.  \n\n3.how to run?\n\u003e SimCSE： python train.py  \n\u003e ESimCSE： python ESimCSE_train.py\n\n4.Result (un-supervised)  \n**spearman corrcoef** is shown as result below:\n\n| Model     | un_supervised |\n|-----------|---------------|\n| Bert_base | 0.538         |   \n| SimCSE    | 0.692         |\n| ESimCSE   | 0.707         | \n\n说明：原论文的无监督SimCSE基于英文，从维基百科上挑了100万个句子进行训练的。本项目评测实验是在中文数据集STS-B(已上传)，实现结果以[苏剑林科学空间结果](https://spaces.ac.cn/archives/8348) 对照。\nSimCSE结果与其一致。  \n![img.png](./data/pic/img.png)    \n**以上供参考，码代码不易，有用请点个赞喔。**    ","funding_links":[],"categories":["文本匹配 文本检索 文本相似度"],"sub_categories":["其他_文本生成、文本对话"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxinyi-code%2FSimCSE-Pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fxinyi-code%2FSimCSE-Pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fxinyi-code%2FSimCSE-Pytorch/lists"}