Comments (2)
Thank you for sharing your excellent work. I would like to know what kind of GPU configuration SERAC ROME MEND needs when editing thousands of samples respectively, and how much time will it take
Speaking empirically,
- For ROME: I do not recommend that you edit thousands of samples sequentially, as this will cause the original model weights to be completely corrupted. Its editing capacity is around 100, you can refer to the paper at https://arxiv.org/abs/2305.13172
- For SERAC: Taking the model around
6B-7B
as an example, the cost of SERAC training is about3h
. Each editing takes only0.5s
, theVRAM
usage is about60GB
in the training phase, and about45GB
in the inference phase - For MEND: Its resource consumption is comparable to that of serac. However, its editing capacity is only 10 cases(see https://arxiv.org/abs/2305.13172). I also do not recommend that you use this method for sequential editing.
from easyedit.
If your problem has been resolved, please help close this issue.
from easyedit.
Related Issues (20)
- Llama2 ROME index out of bound HOT 4
- ROME + GPT-2XL + zSRE replicate results HOT 6
- ROME + llama-2-7b +" Can't load the configuration of './hugging_cache/llama-2-7b'" HOT 9
- Any batch size to recommend for MEMIT batch edit? HOT 4
- does not appear to have a file named config.json HOT 2
- personality edit code HOT 1
- personality edit code
- personality edit code
- Does EasyEdit support training on H800? HOT 5
- L1-distance between original and edited model weights is 0!! HOT 2
- Knowledge Editing with BERT on FEVER Dataset HOT 1
- 在使用KN编辑Chatglm2-6b时出现TypeError报错 HOT 2
- Test case for ChatGLM2 HOT 2
- KN doesn't work on Llama model HOT 6
- Provide MEND and SERAC trained models HOT 9
- Implement performance on ground truth in pre and post measures HOT 1
- Git too fast, can't see the result. HOT 1
- 能否出个qwen的相关tutorial HOT 4
- About Baichuan HOT 2
- I use two A40 GPUs and KN to edit llama2-7b. But the result is still OOM. HOT 5
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.