zankner/Hydra

Issues

• Weights are shared across the MLP layers

  #8 opened 2 months ago by 0seba
  1

• Dockerfile setup for training and inference

  #7 opened 7 months ago by gangooteli
  1

• About 'Cross-Attention_head'

  #6 opened 8 months ago by xinlong-yang
  2

• OOM issue

  #4 opened 8 months ago by ShivangiAg
  2

• Eagle implementation

  #5 opened 8 months ago by FatPigeorz
  1

• The difference and connection between _grounded_proposal and _ungrounded_proposal

  #3 opened 8 months ago by reflectionie
  5

• how to train 30B model

  #2 opened 9 months ago by MeJerry215
  1

• `hydra/data/partition_train_test.py` is missing

  #1 opened 10 months ago by ttim
  1