Meituan-AutoML/VisionLLaMA

Issues

• 关于 2D RoPE implementation x, y pos 顺序的问题

  #4 opened 4 months ago by yihaocs
  1

• If VisionLlama causal masked?

  #6 opened 4 months ago by ma-xu
  1

• 关于 VisionLLama参数量的疑问

  #5 opened 6 months ago by HL4214
  1

• the specific implementation of VisionLLama

  #3 opened 7 months ago by xubin04
  1

• Does it able to connect with llama for image understanding?

  #1 opened 8 months ago by lucasjinreal
  1

• How about image generation for out-of-domain sizes?

  #2 opened 8 months ago by LinB203
  1