Open cornzz opened 1 month ago
Hi @cornzz, thanks for your interest in LLMLingua.
@iofu728 thanks a lot for your response!
Regarding 3: is this what is referred to in the last paragraph of section 4.2 in the paper?
our approach can be readily integrated into the coarse-to-fine framework proposed in LLMLingua (Jiang et al., 2023a), allowing for a higher compression ratio of ∼15x for tasks involving multiple demonstrations or documents.
Describe the issue
Hi,
I have two questions:
Appendix L of the LLMLingua-2 paper talks about allowing the compressor to adjust the compression rate for different samples, but I cannot find any documentation about this in the git repo and looking at
compress_prompt_llmlingua2()
it seems like it is not possible? Also, I dont quite understand from the explanation in appendix L, how this dynamic compression is supposed to work, where can I find more details?What is the
use_context_level_filter
parameter for?