{"id":18983793,"url":"https://github.com/metaglm/lawglm","last_synced_at":"2025-04-06T04:08:17.810Z","repository":{"id":258768140,"uuid":"826176066","full_name":"MetaGLM/LawGLM","owner":"MetaGLM","description":"探索 LLM 在法律行业的应用潜力","archived":false,"fork":false,"pushed_at":"2024-12-10T12:47:38.000Z","size":8411,"stargazers_count":85,"open_issues_count":0,"forks_count":17,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-03-28T18:17:42.868Z","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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MetaGLM.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":"2024-07-09T08:08:16.000Z","updated_at":"2025-03-21T14:51:47.000Z","dependencies_parsed_at":"2024-10-27T09:35:41.407Z","dependency_job_id":"9c73bc39-49de-4714-9b71-db5169ce5367","html_url":"https://github.com/MetaGLM/LawGLM","commit_stats":null,"previous_names":["metaglm/lawglm"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MetaGLM%2FLawGLM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MetaGLM%2FLawGLM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MetaGLM%2FLawGLM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MetaGLM%2FLawGLM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MetaGLM","download_url":"https://codeload.github.com/MetaGLM/LawGLM/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247430869,"owners_count":20937874,"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":"2024-11-08T16:18:34.217Z","updated_at":"2025-04-06T04:08:17.716Z","avatar_url":"https://github.com/MetaGLM.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LawGLM\n\n## 仓库介绍\n\n本仓库是关于2024年琶洲算法大赛的开源代码汇总， 旨在探索大语言模型在法律行业的应用潜力。 本仓库存放了数个比赛团队的竞赛原始代码，均经过整理并开源。\n\n\u003e 关于本次LawGLM比赛及开源项目的背景情况及台前幕后的故事，请参考 [文档](remain_true_to_our_original_open-source_aspiration_in_the_legal_industry.md)。\n\n+ 比赛链接和介绍: https://tianchi.aliyun.com/competition/entrance/532221\n+ 技术： 参赛选手们使用了 Function Call，RAG，长文本等多项技术，让大模型在法律领域发挥了更大的作用。\n+ 模型： 比赛选手的灵活使用 `GLM-4-Air`，`GLM-4-AirX`，`GLM-4-Plus`，`GLM-4-Flash` 等多种 GLM API系列模型。\n  充分发挥 `GLM-4-AirX` 响应快，`GLM-4-Flash` 免费，`GLM-4-Plus` 精度高等优势，结合使用，实现高性价比解决方案。\n\n## 项目更新\n\n- 🔥🔥 **News**: ```2024/12/03```: [2024金融行业·大模型挑战赛](https://competitions.zhipuai.cn/matchDetail?id=120241202000000003) 已经正式推出，持续开源！欢迎报名参赛。\n- 🔥 **News**: ```2024/11/30```: 我们将会公开视频教程，方便大家学习。\n- 🔥 **News**: ```2024/10/20```: 我们整理开源了第一个参赛队伍的代码。并完成了项目的基础工作。\n\n## 比赛规则\n\n### 答疑和规则\n\n+ 官方QA视频: https://www.bilibili.com/video/BV1k4421U78c/?vd_source=c083324a69ff411499cf1b5f539eaac7\n+ QA PPT: [点击这里](assets/qa.pdf)\n+ 官方解题思路： https://www.bilibili.com/video/BV1k4421U78c/?vd_source=c083324a69ff411499cf1b5f539eaac7\n\n### BaseLine\n\n+ [伍柒](assets/【baseline分享】伍柒.pdf)\n+ [法外张三](assets/【baseline分享】法外张三.pdf)\n+ [张江高科](assets/【baseline分享】张江高科.pdf)\n\n以上信息可供参考，进一步了解该比赛。\n\n## 队伍代码\n\n+ [APIWeaver](APIWeaver-lawGLM/README.md): 由 [MeiPixel](https://github.com/MeiPixel) 贡献。\n  支持文档召回, 通过大模型对话式优化prompt, 运行记录转化为llama factory训练格式 ,一键部署gradio等多样功能。\n+ [Vinlic](Vinlic-lawGLM/README.md): 由 [Vinlic](https://github.com/Vinlic)\n  贡献。Vinlic队在第三届琶洲算法大赛GLM法律行业大模型挑战赛道中提出了两种方案：方案A结合多轮迭代与FunctionCall实现Token节省，方案B结合多轮迭代、Planner与CodeAct实现更高自由度。\n+ [Move_forward_every_da](Move_forward_every_day-lawGLM/README.md): 每天前进30公里团队的终版（复赛）方案。复赛成绩排名第15名。\n+ [NickolasNi](NickolasNi-LawGLM/README.md): 由 NickolasNi 贡献，初赛方案。\n+ [LegalHi](LegalHi-LawGLM/README.md): LegalHi 团队方案，通过意图分类，问题改写，思维链、结果判断、外反思等多个步骤，优秀完成任务。\n+ [Buycabbage-semi](Buycabbage-semi-LawGLM): 基于GLM多智能体协同的法律行业问答系统，由买白菜不砍价提供的复赛解决方案。\n\n## 开源协议\n\n本代码中无特殊说明或者无注名额外协议的，均使用 [Apache 2.0](LICENSE) 协议。\n\n## 贡献指南\n\n我们欢迎任何参与比赛的队伍提交自己的比赛作品。\n\n如果您想参与贡献，请参考 [这里](assets/contribute_zh.md)\n\n我们感谢来自以下开发者的贡献，如果名单有却是，请您联系我们：\n\n[![lawglm contributors](https://contrib.rocks/image?repo=metaglm/lawglm\u0026max=2000)](https://github.com/metaglm/lawglm/graphs/contributors)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmetaglm%2Flawglm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmetaglm%2Flawglm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmetaglm%2Flawglm/lists"}