bpe-openai: allow lazy loading BPE and feature flag each model

The fully generated `.dict` models take 70mb, which bloats binaries substantially. This is compared to 3.4mb for the targz.

It would be nice to support lazily doing this translation, which takes a modest hit to runtime performance in return for dramatically smaller binary, and the ability to only load certain models reducing memory consumption.

It would also be nice to have feature flags to turn off certain models; this is less important if we add lazy loading, though, as it would just allow you to save 1-2mb off the binary.

该 issue 没有指出任何文件、测试或入口点；首先定位由 bpe-openai 生成的 .dict 模型，以及用于转换或加载它们的代码。完成标准是：模型可以延迟加载，可以通过 feature flags 选择单个模型，并且在不丢失受支持行为的情况下证明二进制文件和内存的节省。

由索引模型根据 Issue 内容生成。