{"id":13754254,"url":"https://github.com/wakafengfan/simcse-pytorch","last_synced_at":"2025-05-09T22:31:33.672Z","repository":{"id":106373149,"uuid":"362402214","full_name":"wakafengfan/simcse-pytorch","owner":"wakafengfan","description":"pytorch版simcse无监督语义相似模型","archived":false,"fork":false,"pushed_at":"2021-05-13T04:20:43.000Z","size":14,"stargazers_count":22,"open_issues_count":3,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-11-16T07:33:14.825Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","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/wakafengfan.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,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2021-04-28T08:57:03.000Z","updated_at":"2024-03-18T09:33:10.000Z","dependencies_parsed_at":null,"dependency_job_id":"41cc501d-8056-4e8b-93bc-c2768ed31d16","html_url":"https://github.com/wakafengfan/simcse-pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wakafengfan%2Fsimcse-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wakafengfan%2Fsimcse-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wakafengfan%2Fsimcse-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/wakafengfan%2Fsimcse-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/wakafengfan","download_url":"https://codeload.github.com/wakafengfan/simcse-pytorch/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253335699,"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":"2024-08-03T09:01:52.230Z","updated_at":"2025-05-09T22:31:32.000Z","avatar_url":"https://github.com/wakafengfan.png","language":"Python","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"],"readme":"# simcse-pytorch\n\n最近出圈的无监督语义表示模型simcse，依然是基于苏神的keras版本改造的pytorch版本，\n先占坑待后续补充更多实验，并补充Danqi女神的pytorch版本在中文上效果\n\n目前仅实验了roberta-wwm在LCQMC上无监督训练效果，评测指标是Spearman correlation\n\n\n| Model                      | correlation score | \n| -------------------------- | ----------------- | \n| `roberta-wwm`              | 0.67029           | \n| dropout_rate=0.1           |                   | \n| learning_rate=1e-5         |                   |\n| pooling: first-last-avg    |                   | \n| `roberta-wwm(no training)` | 0.60377           | \n| pooling: first-last-avg    |                   | \n\n\n### 环境\n\n- python==3.6.*\n- pytorch==1.8\n- transformers==4.4.2\n\n### 参考\nSimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/pdf/2104.08821.pdf\nhttps://kexue.fm/archives/8348","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwakafengfan%2Fsimcse-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fwakafengfan%2Fsimcse-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fwakafengfan%2Fsimcse-pytorch/lists"}