Skip to content

Issues: hiyouga/FastEdit

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

19 Open 8 Closed
19 Open 8 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

更大模型进行编辑会报OOM问题
#30 opened Jul 4, 2024 by echo-valor
尝试了下baichuan13b，似乎效果不是很好
#29 opened May 24, 2024 by tianmala
[Llama-2-7b-chat] RuntimeError: expected scalar type Float but found Half
#27 opened Oct 20, 2023 by tczbzb
7
训练方式和LLaMA-Efficient-Tuning-main区别
#25 opened Oct 10, 2023 by yiGKTOL
请问编辑后的模型储存在哪里了
#24 opened Sep 24, 2023 by mumuyeye
3
运行时报错 pending This problem is yet to be addressed.
#23 opened Sep 17, 2023 by mumuyeye
2
RuntimeError: computing v Vector
#22 opened Sep 5, 2023 by MaximIfergan
qwen support enhancement New feature or request
#21 opened Aug 17, 2023 by zlh1992
1
this is not a good idea, may lead to severe overfitting.
#19 opened Aug 5, 2023 by dhrhzz
1
LLaMA-2-7b-chat Editing failed pending This problem is yet to be addressed.
#18 opened Aug 3, 2023 by MIracleyin
单张80G卡编辑7B模型 报显存不足 想请教一下如何单机多卡去run pending This problem is yet to be addressed.
#16 opened Jul 27, 2023 by zhangfan-algo
2
这种编辑的方式有副作用吗？比如模型遗忘问题
#15 opened Jul 25, 2023 by runvyang
2
使用在线量化的baichuan 13b chat 报错 LookupError: model.layers.5.mlp.down_proj.weight
#14 opened Jul 24, 2023 by allendred
3
编辑完的baichuan-13b该如何保存
#11 opened Jul 17, 2023 by sichehu
3
Would you consider supporting ChatGLM2-6B?
#10 opened Jul 14, 2023 by zhuam
5
Error occurs when editing Baichuan-13B solved This problem has been already solved.
#7 opened Jul 11, 2023 by hiyouga
2
Why modifying down_proj in llama?
#5 opened Jul 10, 2023 by Wenyueh
1
初步看起来，这个的原理是，捕捉到两个data在模型内部的参数diff？
#4 opened Jul 10, 2023 by guotong1988
Is there any way to apply this interesting algorithm to the chatGLM-6B or chatGLM2-6B models?
#3 opened Jul 10, 2023 by rayoa
2
ProTip! no:milestone will show everything without a milestone.