hao-ai-lab/Consistency_LLM

Issues

• Only has 0.44 accuracy on GSM8K after running the provided codes

  #13 opened 5 months ago by TrueNobility303
  7

• AttributeError: 'LlamaModel' object has no attribute '_use_flash_attention_2'

  #10 opened 6 months ago by raghavgarg97
  2

• Spider results higher than paper.

  #16 opened 4 months ago by jacklishufan
  0

• How to combine lookahead with cllms?

  #15 opened 5 months ago by jianyuheng
  0

• Acceleration for batch Inference ?

  #14 opened 5 months ago by jianyuheng
  0

• Model collapse

  #11 opened 6 months ago by TrueNobility303
  8

• Reproduce Table 1 by this repo?

  #6 opened 6 months ago by dreaming-panda
  6

• Error occured when i train the model

  #9 opened 6 months ago by littletomatodonkey
  5

• Changes needed?

  #8 opened 6 months ago by sdmorrey
  0

• Is the generation greedy-decoding?

  #4 opened 7 months ago by w32zhong
  1