FreedomIntelligence/LongLLaVA

Issues

• Consider evaluating on LongVideoBench

  #15 opened a month ago by teowu
  1

• LongLLava-Med

  #13 opened 2 months ago by LongYu-LY
  4

• CT frame numbers and frame resolution

  #14 opened 2 months ago by ruian1
  1

• repository not found, token with permission

  #11 opened 3 months ago by adelightday
  2

• additional auxiliary loss for moe?

  #12 opened 3 months ago by maxin-cn
  2

• Can you provide the model path of longllava-9b?

  #9 opened 3 months ago by xuzukang
  1

• device spec to run the inference

  #8 opened 3 months ago by adelightday
  4

• How to switch model from 13b to 9b

  #10 opened 3 months ago by xuzukang
  2

• the role of moe

  #7 opened 3 months ago by maxin-cn
  2

• There are many bugs when pip the requirement.txt as follows, making the code hard to run, can you provide more details?

  #4 opened 3 months ago by Messi2013
  1

• ImportError: cannot import name 'LlavaPhiForCausalLM' from 'llava.model'

  #5 opened 3 months ago by Jeremy-J-J
  1

• Missing supporting init.sh and VisionJamba found when running MultiImageSFT.sh

  #3 opened 3 months ago by MXC66ai
  2

• Architecture of LongLLaVA

  #6 opened 3 months ago by maxin-cn
  1

• Appreciation for the Influence on VLM and Inquiry about LLM Foundation

  #2 opened 4 months ago by CuriousCat-7
  1