bytedance/lynx-llm

Issues

• paper says adapters are added every M blocks(M=1) but checkpoints seems to add every two

  #7 opened a year ago by Maxlinn
  2

• How is the dimension of pos_embed handled when the image size is increased to 420x420 in the pre-training phase?

  #6 opened a year ago by yutaidong
  2

• Pretrained models

  #4 opened a year ago by yuntaodu
  1

• Could you please provide the pictures and videos used by benchmark for convenience?

  #3 opened a year ago by ycsun1972
  1

• Prompt during training and inference

  #2 opened a year ago by vateye
  3

• when the training script will be released?

  #1 opened a year ago by JiaweiZhao-git
  7