Ablustrund/LoRAMoE
LoRAMoE: Revolutionizing Mixture of Experts for Maintaining World Knowledge in Language Model Alignment
Python
Issues
- 0
请问微调实验需要多少显存
#12 opened by Liukairong2023 - 8
【bug】代码无法运行
#5 opened by Liukairong2023 - 2
求指教!!请问论文中的Router模块对应代码的哪部分内容呢
#11 opened by 1009073362 - 0
使用opencompass评估模型出错
#10 opened by qxpBlog - 1
[bug] 代码运行出错!!急!急!非常感谢!
#9 opened by SXxinxiaosong - 3
请问训练完毕,如何进行generation
#6 opened by fzp0424 - 1
训练数据中的"task_type"的作用
#8 opened by guihonghao - 4
transformers版本问题
#7 opened by lzw-lzw - 4
训练保存下来的模型不是完整的模型,无法使用opencompass评估
#4 opened by hy010227 - 1
Potential Bug in Paper or Code
#3 opened by chengeharrison - 3
Missing evaluation file
#1 opened by 2018211801 - 1