Comments (1)
Thanks for your interest in EasyEdit, you encountered this bug due to memory overflow caused by backpropagation.
From a practical point of view, you'll need about 60-80 GB
of VRAM to train llama-2-7B
using MEND.
You can refer to the following solutions:
- Increase VRAM
- Use
accelerate
(https://github.com/huggingface/accelerate) for the model parallel - Change to another editing method (such as
ROME
)
from easyedit.
Related Issues (20)
- Question about the function edit_dataset in EasyEdit-main/easyeditor/editors/editor.py HOT 2
- Compiling code for WikiData_counterfact and Wikidata_recent HOT 8
- Question about SERAC HOT 2
- Error when runing function test_IKE_Blip2OPT_VQA() in multimodal_edit.py HOT 3
- Error when Running IKE for Wiki Counterfactual dataset HOT 10
- Builder config error when running MEMIT HOT 9
- Differences between ft_main.py and lora_main.py HOT 2
- Full datasets loading fix HOT 1
- There is a question about 'edited_model' in easyeditor/editor.py, why edit() function always return the last edited_model only? HOT 5
- Model edition does not take effects HOT 6
- 请问是否可以设置随机种子? HOT 8
- How to apply it to new models HOT 5
- Request for 'Editing GPU memory usage' update HOT 2
- MMEdit config description HOT 15
- MEMIT方法是否能使每次的权重更新相同(在代码完全一致的情况下) HOT 6
- Problems about the results of GRACE method on Llama-2-7b HOT 13
- 请问一下论文中提到的opencompass在评估时要用到吗 HOT 2
- T-Patcher support HOT 2
- Question about E-VQA HOT 8
- Could there be a bug in the FT implementation HOT 6
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from easyedit.