lucidrains/self-rewarding-lm-pytorch

Issues

• usage demo is not working

  #32 opened 25 days ago by 652994331
  0

• UnboundLocalError: local variable 'self_reward_model' referenced before assignment

  #24 opened 5 months ago by UbeCc
  3

• What's the reference model for DPO?

  #31 opened 8 months ago by Draconda
  1

• OSError: [Errno 22] Invalid argument: 'preference_seq.memmap.npy'

  #30 opened 9 months ago by Oloup
  0

• ModuleNotFoundError: No module named 'x_transformers'

  #25 opened 10 months ago by mayankpathaklumiq
  1

• What changes should I make to apply the method on Llama2?

  #23 opened 10 months ago by Labmem009
  0

• I encountered the following error when trying to run usage

  #21 opened 10 months ago by Yanfors
  1

• How to use HF Transformers model

  #10 opened a year ago by fakerybakery
  3

• TypeError: tuple indices must be integers or slices, not tuple

  #18 opened a year ago by fakerybakery
  1

• RuntimeError: Placeholder storage has not been allocated on MPS device!

  #15 opened a year ago by fakerybakery
  2

• Multiple GPUs

  #14 opened a year ago by fakerybakery
  0

• Why use a custom sample function instead of original HuggingFace generate() function?

  #11 opened a year ago by scarydemon2
  1

• The reward prompt is weak.

  #7 opened a year ago by Minami-su
  6

• Default `iteration` about SPIN. (Reward model~Policy model)

  #9 opened a year ago by KyujinHan
  1

• run spin demo

  #8 opened a year ago by westlongtime
  3

• Is this work in progress?

  #4 opened a year ago by jbdatascience
  4

• Help with Setting up and running ?

  #3 opened a year ago by badboysm890
  1

• code and dataset？

  #1 opened a year ago by wanghao-007
  0