Comments (1)
Great question. The underlying principles in our work do not leverage any knowledge of the domain, and thus should be applicable to vision and audio transformers as well. That being said, we haven't got the chance to test whether it actually works. Please feel free to try it out and let us know your experience!
from retraining-free-pruning.
Related Issues (14)
- Use your Code for other classification datasets
- Any experiments on NLG tasks?
- Can this be used for detection, segmentation, and other tasks?
- Hi, can this "the three-stage decomposition of the pruning process" be applied to GPT-X or any other NLG task? And how this could be done?
- Test Accuracy function is a bit too slow HOT 1
- What is the purpose of setting "encoder.layers" and how does it differ from "encoder.layer" ? HOT 2
- Question about the pruned model.
- GLUE & SQuAD Metadata
- Missing datasets file? HOT 2
- Real-time inference results HOT 4
- About the speedup performance of the code HOT 1
- why bert-base-uncased model set constraint to 0.5, qqp test accuracy only 0.3743 HOT 2
- dependency package versions HOT 1
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 retraining-free-pruning.