知识卡片
能分词不等于会用该语言
某语言单词能作为完整 token 编码,只说明 tokenizer 词表和编码行为,不足以证明语言模型理解或生成该语言的能力。即使 tokenizer 与模型常一起训练,能力仍需由语言任务样本和质量标准检验。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 附录B 练习答案
原书出处 · 1 处
- · 查看原书依据
German words are not broken down into characters or even subwords here, suggesting that the tokenizer has seen German texts during training. This also suggests that the LLM was likely trained on German texts, too, and should be able to handle at least certain non-English languages well.
参考来源
- 位置:《Build a Reasoning Model (From Scratch)》第08章《附录B 练习答案》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Build a Reasoning Model (From Scratch)/_epub-src/OEBPS/Text/appendix-b.html)
- 结论依据:摘录中关于能分词不等于会用该语言的定义、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:German words are not broken down into characters or even subwords here, suggesting that the tokenizer has seen German texts during training. This also suggests that the LLM was likely trained on German texts, too, and should be able to handle at least certain non-English languages well.