The script for LongChat to reproduce the LongLLMLingua

microsoft / LLMLingua

[EMNLP'23, ACL'24] 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

4.63k stars 256 forks source link

The script for LongChat to reproduce the LongLLMLingua #43

Open zhyunlong opened 10 months ago

zhyunlong commented 10 months ago

Very appreciate your awesome work and efforts for the easy-to-use code.

The provided example uses OpenAI's GPT3.5 with the OpenAI API. Is there a plan to provide the evaluation script using longchat-13b-16k to reproduce LongLLMLingua?

iofu728 commented 10 months ago

Hi @zhyunlong, thank you for your support with LLMLingua.

We utilize the same script as 'lost in the middle'. You can access the script at this link.