microsoft / LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.
https://llmlingua.com/
MIT License
4.46k stars 248 forks source link

what is 1-shot / half-shot /quarter-shot constraint in experiments? #185

Open 21-10-4 opened 4 days ago

21-10-4 commented 4 days ago

我还是无法理解。1-shot constraint代表the original token(包含一个示例) ,half-shot constraint指什么,半个示例?

Originally posted by @21-10-4 in https://github.com/microsoft/LLMLingua/issues/164#issuecomment-2367944467

21-10-4 commented 4 days ago

非常期待回复,感谢

cornzz commented 11 hours ago

I was also wondering that...