当前位置:首页 > 报告详情

选择以 Meta 和乔克托族为特色的最佳开源 LLM [LRN1224].pdf

上传人: Fl****zo 编号:971065 2025-11-08 49页 3.52MB

1、 LRN 1224:Select the Best Open Source LLMs Featuring Meta and The Choctaw Nation of OklahomaWendy YipSenior Product Manager,OCI Data SciencePeter ZaffinaDirector of IT Enterprise Services Engineering,Choctaw NationAmir YoussefiPartner Engineer,MetaCopyright 2025,Oracle and/or its affiliates 2The fol

2、lowing is intended to outline our general product direction.It is intended for information purposes only,and may not be incorporated into any contract.It is not a commitment to deliver any material,code,or functionality,and should not be relied upon in making purchasing decisions.The development,rel

3、ease,timing,and pricing of any features or functionality described for Oracles products may change and remains at the sole discretion of Oracle Corporation.Safe harbor statement3Copyright 2025,Oracle and/or its affiliatesAgenda4Copyright 2025,Oracle and/or its affiliatesWhat is an open source model

4、and why use it?Considerations for choosing an open source modelUsing open source models in OCI Data ScienceOpen source model use case:Choctaw language preservation projectIntroduction to Llama modelsWhat is an open source model?5Copyright 2025,Oracle and/or its affiliatesClosed source modelOpen sour

5、ce modelA proprietary model that is restricted for private use.The source code and weights are not available to publicDeveloped in a way that makes source code available to anyone in the public domain to use and modifyOpen weight modelSource code is kept private but model weights are available in th

6、e public domain to useWhy use Open Source models?6Copyright 2025,Oracle and/or its affiliates Latest innovationsWhy use Open Source models?7Copyright 2025,Oracle and/or its affiliatesLatest innovationsCommunity participationWhy use Open Source models?8Copyright 2025,Oracle and/or its affiliatesLates

word格式文档无特别注明外均可编辑修改,预览文件经过压缩,下载原文更清晰!
三个皮匠报告文库所有资源均是客户上传分享,仅供网友学习交流,未经上传用户书面授权,请勿作商用。
根据报告的内容,全文主要内容概括如下: - **开源模型介绍**:介绍了开源模型与闭源模型的区别,以及使用开源模型的优势,如创新、社区参与、成本节约、透明度和灵活性。 - **选择开源模型考虑**:强调了明确用例、确定性能标准与成本限制、比较和评估不同模型的重要性。 - **OCI数据科学应用**:展示了如何使用OCI数据科学平台工作与开源生成式AI模型,包括加速数据科学生命周期、使用Python工具和框架、企业级安全性和多用户支持等。 - **Choctaw语言保护项目**:介绍了Choctaw语言保护项目如何利用开源AI进行定制化、隐私保护和规模化。 - **Llama模型介绍**:详细介绍了Llama模型系列,包括不同版本的特点、性能和适用场景。 - **Llama Stack工具**:介绍了Llama Stack,这是一个用于构建AI应用的标准化核心组件。 - **Llama Prompt Ops**:介绍了Llama Prompt Ops工具,用于优化Llama模型的提示,提高性能和可靠性。 核心数据: - Choctaw语言使用者约300人。 - Llama 3.1模型支持多语言性能。 - Llama 4 Scout模型支持10M上下文窗口。
"开源LLM,如何选?" "Choctaw语言如何用AI传承?" "Llama模型,多模态新体验!"
客服
商务合作
小程序
服务号
折叠