Comments (2)
Bachstelze
commented on May 31, 2024
How can we add more models?
We could analyze instructions models with flan-t5.
from attention-viz.
catherinesyeh
commented on May 31, 2024
Hi, we have not tried flan-t5 yet, but if you can get the data in a similar format as the provided gpt or bert data, you can substitute that in when running the application. Streamlining this process is an area for future work, as currently, adding new models may require modifications to both the frontend and backend.
from attention-viz.
Related Issues (20)
- Show all queries + keys on click
- 2D colormap for positional embedding of VIT HOT 1
- Try different datasets
- Show related heads in single view
- Label points in attention line view
- Attention Visualization for Image (VIT) HOT 1
- Give more meaningful label to the image patches HOT 1
- Using more accurate off-the-shelf model for labeling image patches
- Control label density via slider HOT 2
- Display sparsity of attention patterns
- Display CLS token for VIT-16/32 HOT 1
- Attention Arrow Visualization for VIT-16/32 HOT 1
- Other encodings to try for text
- Color by sentence length
- Errors running: npm run server on MacOS 13.4 HOT 1
- text to image view HOT 1
- ERROR Cannot read properties of undefined (reading 'position') HOT 1
- Attention-viz with new models and datasets? HOT 1
- https://attentionviz.com/ fails to load because it attempts an http pull (not https) HOT 3
- What is version of nodejs and npm needed to run this tool? HOT 2
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 attention-viz.