Aaronhuang-778/SliM-LLM

Issues

• Calculating saliency of weight

  #7 opened a month ago by kiucho
  0

• Does it support the LLAMA3-8B-INSTRUNCT and QWEN2-7B-INSTRUCT?

  #4 opened a month ago by LiMa-cas
  3

• Clarification on Theorem 1 of the Paper

  #6 opened a month ago by kiucho
  4

• Cannot reproduce

  #5 opened a month ago by haoming-codes
  2

• the quantized bit width

  #3 opened 4 months ago by xiaxin1998
  2

• How about the performance of Slim-LLM on 4-bit model?

  #2 opened 5 months ago by ZorkJ
  6

• readme: requirement.txt -》requirements.txt

  #1 opened 5 months ago by tellyoung
  1