ziqipang/LM4VisualEncoding

Issues

• Influence of ViT

  #11 opened 4 months ago by jiazhen-code
  1

• curious about which llama checkpoint

  #10 opened 4 months ago by 944104439
  2

• 2D VQA and Image-Text Retrieval

  #6 opened a year ago by xvolica
  3

• LLMBoostMedical

  #9 opened 10 months ago by daydayupzzl
  4

• About Motion Forecasting

  #8 opened a year ago by Zbozhou
  0

• Sharing experiments in lung sound abnormal detection, and suggestion, add random initialization weights of LLM layer experiments.

  #7 opened a year ago by QiaoranC
  0

• Some questions about ViT-Small-LLaMA

  #4 opened a year ago by 1090h2400
  1

• About importing pre-trained weights for the LLaMA model

  #3 opened a year ago by Changwei-Ouyang
  2

• Is there any ablation studies on the number of LLM layers inserted between the visual encoder and classifiers?

  #2 opened a year ago by valencebond
  1