LeapLabTHU/MLLA

Issues

• Definitional Problems with Forget Gates

  #26 opened 5 months ago by lazywu170101
  0

• runing errors

  #24 opened 5 months ago by gaoGyr
  1

• 关于输入图像尺寸必须为正方形

  #22 opened 5 months ago by ycwsilent
  5

• Several questions about rope and linear-attention

  #25 opened 5 months ago by Journey7331
  2

• runing Error

  #23 opened 5 months ago by gaoGyr
  1

• A positional encoding is used instead of the forget gate

  #12 opened 6 months ago by LQchen1
  1

• About Table 1

  #21 opened 5 months ago by leily578
  2

• Why remove `focusing_factor`?

  #20 opened 6 months ago by Journey7331
  1

• the ELU activation function

  #19 opened 6 months ago by Journey7331
  2

• Unfair comparison in table3 of MLLA paper.

  #15 opened 6 months ago by wullia
  5

• Potential Inaccuracy in FLOPs Computation

  #18 opened 6 months ago by wullia
  2

• About the Fig.4(a)

  #17 opened 6 months ago by 1056891520
  1

• Excellent work! Any plans to apply MLLA to diffusion models?

  #16 opened 6 months ago by sudo-lucky
  1

• UserWarning: ComplexHalf support is experimental and many operators don't support it yet. (Triggered internally at ../aten/src/ATen/EmptyTensor.cpp:30.)

  #14 opened 6 months ago by ray-lee-94
  1

• code for object detection and segmentation

  #13 opened 6 months ago by ShixuanGu
  0

• about MESA

  #11 opened 7 months ago by LQchen1
  6

• about training speed

  #5 opened 7 months ago by LQchen1
  11

• 数据集

  #9 opened 7 months ago by ylrccc
  1

• MLLA是否可以改成训练3D图像？

  #6 opened 7 months ago by W-Kinlon
  1

• Request for Training Logs

  #10 opened 7 months ago by YuHengsss
  0

• How's the performance on language task since the forget gate has been replaced?

  #7 opened 7 months ago by kyrie-23
  3

• Confusing about shortcut

  #8 opened 7 months ago by kyrie-23
  3

• training time per epoch

  #3 opened 7 months ago by ShixuanGu
  3

• Is it possible to use selective scan in MLLA?

  #4 opened 7 months ago by IceClear
  4

• Single-head or multi-head?

  #2 opened 7 months ago by patronum08
  6

• What is the meaning of token length in Normalization?

  #1 opened 7 months ago by EricLina
  2