feizc/MLE-LLaMA

Issues

• 请问english-chinese alignment dataset如何使用？

  #9 opened a year ago by acadaiaca
  0

• 能否介绍更多关于english-chinese alignment dataset的细节呢？

  #8 opened 2 years ago by nlp4whp
  1

• What is the version of transformers?

  #7 opened 2 years ago by misonsky
  0

• When will release the checkpoints for fine-tuned 7B LLaMA model?

  #6 opened 2 years ago by zhangsanfeng86
  0

• Question of token vocabulary

  #4 opened 2 years ago by maojinyang
  1

• Question about training step

  #5 opened 2 years ago by 5joon2
  0

• how to train for 30b or 65b on multiple GPU（4x80G）

  #3 opened 2 years ago by lishangjin
  1

• 有训练好的模型吗？

  #1 opened 2 years ago by yuxuan2015
  1

• Trainer: evaluation requires an eval_dataset

  #2 opened 2 years ago by lishangjin
  1