问HN：我该如何判断哪些大型语言模型（LLM）是基于什么数据进行训练的？
我并不是专家，只是在努力跟上进度。但是……<p>我觉得大型语言模型（LLM）是一种微妙的结合，既要懂语言，又要掌握一些事实。如果要制作一个聊天机器人来帮助人们理解他们的税务申报，那么你需要一个能够理解语言的“基础”LLM，然后通过检索增强生成（RAG）添加特定领域的知识。因此，“是的”，要知道星期四在星期三之后；“不”，不需要知道珠穆朗玛峰有多高；而关于所得税的问题必须参考RAG。这正确吗？<p>那么，有现成的“轻量”模型可以用来实现这个吗？自己训练一个更好还是更好？
查看原文
I'm really no expert and attempting to come up to speed. But...<p>It strikes me that LLM's are a subtle combination of knowing the language and knowing some facts. If one were making a chatbot for helping (say) people understand their tax returns then you'd want a 'base' LLM that understood language and then add domain specific knowledge via RAG. So "yes" to knowing that Thursday comes after Wednesday; "no" to knowing how high Everest is; and questions regarding income tax have to reference the RAG. Is this correct?<p>So are there stock "thin" models for doing this? Is it better to train your own?