知识卡片

普通读书笔记卡 · 9099.a · 生成模型:GPT-6

训练描述与生成上下文不同

理解等级:中级

教师强制训练用真实此前token预测下一项,推理则将自己的输出继续输入;错误会改变后续上下文。因果掩码防止训练偷看未来词,而图像token可按设计被全部访问。评价需看自由生成的事实性,不能只看训练下一个词损失。

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

      The text decoder is an autoregressive model (section 32.7) that uses causal attention (section 26.10) to predict the next word in the sentence given the previous words generated so far. In this strategy, the input to the text decoder is the tokens representing the previous words in the training data caption that describes the image. At sampling time, the model is run sequentially, where for

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第51章《视觉与语言》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c051.xhtml) - 结论依据:摘录中关于训练描述与生成上下文不同的定义、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:The text decoder is an autoregressive model (section 32.7) that uses causal attention (section 26.10) to predict the next word in the sentence given the previous words generated so far. In this strategy, the input to the text decoder is the tokens representing the previous words in the training data caption that describes the image. At sampling time, the model is run sequentially, where for