玩转大模型02 大模型只能对话？不！大模型是一个万能的接口
在我们日常使用大模型的时候，都是以对话的形式使用的。它的输出也总是以自然语言的形式展现给我们。但在某些场景，我们更希望能得到结构化的输出，那么我们是否有可能使用大模型的「智慧」，实现一个智能接口，让他能够结构化地输出我们任意想要的数据呢？
#LLM
Mastering Large Models 02: Are Large Models Only for Dialogue? No! Large Models Are a Universal Interface
In our daily use of large models, we typically interact with them through dialogue. Their outputs are always presented to us in natural language. However, in certain scenarios, we prefer to obtain structured outputs. Is it possible to leverage the 'intelligence' of large models to create a smart interface that can output any data we desire in a structured format?
玩转大模型01 大模型也能命中缓存？从KV Cache 到 Prompt Cache
在使用大模型的时候，除了看模型的性能表现，价格（成本）也是一个很重要的参数，不知道你有没有留意过，在大模型 API 价格中，输入价格会分为两种，缓存命中和缓存未命中，缓存命中的时候，价格会更便宜。不仅如此，命中缓存也能减少整体的耗时。这是如何工作的呢？
Mastering Large Models 01 - Can Large Models Hit the Cache? From KV Cache to Prompt Cache
When using large models, besides evaluating the model's performance, price (cost) is also a crucial parameter. Have you noticed that in the pricing of large model APIs, input costs are divided into two categories cache hit and cache miss? When there is a cache hit, the price is cheaper. Moreover, hitting the cache can also reduce the overall time consumption. How does this work?
对推理模型的一些想法
年前 deepseek 推出了 r1 模型，OpenAI 随后也推出了 o3-mini 模型，简单看了一下 deepseek-r1 的论文，对推理模型有一些想法和疑问。