lich99/ChatGLM-finetune-LoRA
Code for fintune ChatGLM-6b using low-rank adaptation (LoRA)
Jupyter NotebookApache-2.0
Issues
- 10
有什么卡训练的,V100完全搞不定
#15 opened by huzaizi2023 - 8
No such file or directory: '/root/.cache/huggingface/modules/transformers_modules/chatglm-6b/tokenization_chatglm.py'
#29 opened by Data2Me - 0
- 0
- 0
不考虑GLM的双向注意力部分,注意力矩阵不是一个下三角矩阵吗
#47 opened by fxb392 - 0
显存问题
#46 opened by zhangsanjava - 3
- 0
作者你好,这个项目对python的版本有什么要求吗,3.7是否可以?
#44 opened by tjulh - 3
ValueError: 150004 is not in list是什么回事?
#28 opened by z1968357787 - 8
peft 0.3.0如何设置adapater_name
#38 opened by moseshu - 0
while cnt < retry_cnt:
#43 opened by fxb392 - 0
问答数据集如何构建
#42 opened by Godlikemandyy - 1
[deepspeed] OVERFLOW!
#30 opened by JingerAI - 0
- 3
关于ZeRO的疑问?
#33 opened by MAxx8371 - 0
有大佬们试过用8卡训练的吗?
#40 opened by tu2022 - 0
请问LORA模型参数怎么加载到原模型里呢?
#39 opened by ZeyuBa - 4
finetune没效果
#34 opened by ChenBinfighting1 - 2
context_length = obj['prompt'].index(130004)
#37 opened by moseshu - 3
LoRA训练时间大概是多久呢?
#36 opened by realcarlos - 3
这个显卡要求一定是bfloat16吗
#26 opened by z1968357787 - 1
example.ipynb中进行训练测试loss为nan
#32 opened by SilentMoebuta - 2
torch.distributed.elastic.multiprocessing.errors.ChildFailedError, when running the train_new.py
#27 opened by Skywalker-Harrison - 1
LoRA的A矩阵一直不更新
#22 opened by qz701731tby - 1
关于分布式GPU训练
#25 opened by z1968357787 - 1
example_simple报错
#24 opened by qishisurenhhh - 0
here are my questions,I have more than 4 gpus to run the train.py,but it still out of memory,I check the usage of memory and find that one of them overflows and produce the bug,how can I solve it?
#23 opened by z1968357787 - 2
subprocess.CalledProcessError: Command '['ninja', '-v']' returned non-zero exit status 1.
#17 opened by xiamaozi11 - 0
单机多卡报错
#20 opened by ForgetThatNight - 0
您好,问一下,这个训练完有可以展示与原来基础模型进行对比的测试效果吗
#21 opened by kunshou123 - 8
请问下Finetune之后能实现企业定制FAQ的效果吗?可能有一百个问答这样
#8 opened by terryops - 2
训练loss变为NaN
#19 opened by qz701731tby - 4
能否使用量化后的chatGLM-6b-int4小模型进行微调?
#7 opened by valkryhx - 1
可以给一下具体的环境requirement吗?
#11 opened by Data2Me - 1
训练后的结果对应不上
#4 opened by zhangyanbo2007 - 6
About multi-GPU
#9 opened by zhongtao93 - 1
如何设置batch_size个数,变动后train会变维度上的错误
#12 opened by GUORUIWANG - 1
train.py的命令行启动是什么?
#13 opened by Data2Me - 2
- 6
LORAConfig报错:ValueError: Target modules ['q', 'k', 'v'] not found in the base model. Please check the target modules and try again.
#14 opened by nameless0704 - 0
- 1
- 1
两个epochs之间,loss值并没有降下来
#6 opened by aizpy - 1
- 5
训练超显存
#3 opened by GaoPengGit - 1
数据集和微调模型的一些问题
#2 opened by SarmonFish - 2
Is there any details about dataset?
#1 opened by 980202006