Added unittest for structured_compress_prompt and fixed bugs

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

4.27k stars 228 forks source link

Added unittest for structured_compress_prompt and fixed bugs #95

Closed SiyunZhao closed 4 months ago

iofu728 commented 4 months ago

Todo:

Switching to a customizable parameter;
Add json compress prompt function;
Add documents