知识卡片

普通读书笔记卡 · 8702.a · 生成模型:GPT-6

维度裁剪必须受真实输出约束

理解等级:中级

裁剪点不能超过模型实际输出维度。原书nomic-embed-text-v1.5练习列1024,但所查配置hidden_size为768;应从该版本支持的维度中选择,并分别测召回和成本,不能凭书中数字生成不存在的向量维。

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

      Download this dataset by Rishabh Misra containing news headlines. Use the nomic-embed-text-v1.5 model from Nomic AI, which has been trained using MRL. Pick one of the headlines as the query and generate its query embedding. Generate document embeddings for all other headlines, and calculate similarity scores between query and document embeddings at truncation checkpoints 1,024, 768, 512, 256, and 128.

    参考来源

    - 位置:《Designing Large Language Model Applications》第11章《表示学习与嵌入》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch11.html) - 结论依据:摘录中关于维度裁剪必须受真实输出约束的定义、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:Download this dataset by Rishabh Misra containing news headlines. Use the nomic-embed-text-v1.5 model from Nomic AI, which has been trained using MRL. Pick one of the headlines as the query and generate its query embedding. Generate document embeddings for all other headlines, and calculate similarity scores between query and document embeddings at truncation checkpoints 1,024, 768, 512, 256, and 128.