stanleylsx/llms_tool

Issues

• dpo训练异常

  #46 opened 10 months ago by tuzeao
  16

• sft train报错

  #76 opened 5 months ago by langgege-cqu
  0

• AttributeError: 'DataManager' object has no attribute 'generating_args_preprocess'

  #75 opened 7 months ago by autaugaville
  1

• SFT数据集字段

  #74 opened 7 months ago by FoolMark
  1

• QLora似乎不能和deepspeed zero3一起使用？

  #73 opened 7 months ago by shaomai00
  1

• deepspeed报错

  #72 opened 7 months ago by wq343580510
  0

• 大佬，能尝试做训练用的WebUI吗?

  #69 opened 8 months ago by win10ogod
  1

• 关于模型预训练

  #67 opened 8 months ago by clclclaiggg
  2

• 扩展词表代码需优化

  #65 opened 8 months ago by tiandiweizun
  0

• sft时不输出eval loss

  #60 opened 8 months ago by shaomai00
  3

• baichuan2-13b-chat的deepspeed训练报错，是dpo训练

  #62 opened 8 months ago by MingJiaAn
  0

• 大神能建个微信群或者留个联系方式吗？

  #61 opened 8 months ago by MingJiaAn
  1

• 期待預訓練代碼

  #59 opened 9 months ago by indiejoseph
  1

• 使用prefix-tuning微调Qwen模型时报错

  #47 opened 10 months ago by FelixZhang7
  1

• Pls support RWKV world model

  #4 opened 10 months ago by xiaol
  0

• 关于权重合并

  #42 opened 10 months ago by FelixZhang7
  1

• 可不可以提供一下生成json的脚本，我这边生成的会报错，是编码格式的问题吗？

  #39 opened 10 months ago by FelixZhang7
  4

• 关于权重合并

  #41 opened 10 months ago by FelixZhang7
  0