← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 6759.b · 生成模型:GPT-6

本地推理工具不改写模型许可

理解等级:中级

推理框架负责加载和执行,模型权重仍有其自身许可与获取条件。使用另一工具并不自动消除商业限制或访问约定;应分别核对模型、代码、数据和衍生制品的条款,不能把能运行等同于可任意使用。

这张卡片看不懂?

已有反馈 · 0 条

    还没有人提交反馈。

    在整书笔记中的位置

    原书出处 · 1 处

    • · 查看原书依据

      When working with models behind paywalls or business source licenses, you will need to authenticate with an access token or key to prove you have accepted their terms of service. Fortunately, there are several new ways to run Llama models locally without obtaining permission from Meta. For example, the Llama.cpp20 and Ollama21 projects allow you to compile, fine-tune, and commercially use Llama-2-based models without restriction:

    参考来源

    - 位置:《Natural Language Processing in Action, Second Edition》第10章《真实世界中的大语言模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-10.html) - 结论依据:摘录中关于本地推理工具不改写模型许可的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。 - 原始内容:When working with models behind paywalls or business source licenses, you will need to authenticate with an access token or key to prove you have accepted their terms of service. Fortunately, there are several new ways to run Llama models locally without obtaining permission from Meta. For example, the Llama.cpp20 and Ollama21 projects allow you to compile, fine-tune, and commercially use Llama-2-based models without restriction: