Skip to content

Issues: shuxueslpi/chatGLM-6B-QLoRA

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

25 Open 25 Closed
25 Open 25 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

ChatGLM2-6b模型合并时报错ValueError: We need an offload_dir to dispatch this model according to this device_map, the following submodules need to be offloaded
#50 opened Apr 3, 2024 by Hysy11
ValueError:
#49 opened Feb 19, 2024 by sevenandseven
qlora微调训练随机性
#48 opened Jan 2, 2024 by wbchief
合并模型的时候显存不够,用的4090，24G
#47 opened Dec 1, 2023 by mengxinru
微调后推理性能问题
#44 opened Oct 13, 2023 by daydayup-zyn
1
训练显存有些问题
#43 opened Oct 12, 2023 by WellWang-S
BrokenPipeError: [Errno 32] Broken pipe
#40 opened Sep 20, 2023 by plutoda588
7
transformers>4.30.2时，模型不会进行量化，是因为什么？
#39 opened Sep 19, 2023 by sxm7078
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:1 and cuda:0! (when checking argument for argument target in method wrapper_CUDA_nll_loss_forward)，请问如何调整训练代码，适配多卡训练？？
#38 opened Sep 17, 2023 by jhonffe
1
RuntimeError: mat1 and mat2 shapes cannot be multiplied (588x4096 and 1x9437184) ，ChatGLM2-6B做微调，请问如何设置参数？？
#37 opened Sep 17, 2023 by jhonffe
1
ImportError: libcudnn.so.8: cannot open shared object file: No such file or directory
#36 opened Sep 11, 2023 by Hzzhang-nlp
12
protobuf 和 icetk 版本不兼容
#35 opened Aug 31, 2023 by wisper181
1
merge后模型Loading checkpoint shards Killed
#33 opened Aug 12, 2023 by Derican
6
训练结束后，数据展示出现问题
#32 opened Aug 9, 2023 by HBdingdang
ChatGLM可进行QLoRA微调，但ChatGLM2会报显存OOM
#29 opened Aug 2, 2023 by Y-Bay
12
训练完成后遇到的问题
#28 opened Jul 27, 2023 by AIGeorgeLi
1
chatglm2-6b输入不跟官方的保持统一吗？
#24 opened Jul 14, 2023 by SCAUapc
11
请问模型怎么才能通过deepspeed进行多卡训练
#22 opened Jul 12, 2023 by RayneSun
5
模型微调出现模型部分参数在cpu上面
#21 opened Jul 10, 2023 by kunzeng-ch
3
对chatglm2进行lora微调时，提示CUDA error: invalid argument，麻烦大佬看一下
#19 opened Jul 9, 2023 by LKk8563
2
怎么并行训练？
#18 opened Jul 6, 2023 by bash99
4
微调chatglm-6b占用内存20g以上，什么原因
#17 opened Jul 5, 2023 by sxm7078
8
你好，微调后，提问一些别的问题会出现<UNK>
#13 opened Jul 3, 2023 by SinLT
3
没有docker环境 用git bash运行报错
#12 opened Jun 30, 2023 by Mou-Mou-L
4
qlora 微调效果
#4 opened Jun 27, 2023 by yxk9810
16
ProTip! Find all open issues with in progress development work with linked:pr.