Coder Social home page Coder Social logo

zjunlp / knowledgecircuits Goto Github PK

View Code? Open in Web Editor NEW
35.0 6.0 1.0 989 KB

Knowledge Circuits in Pretrained Transformers

License: MIT License

Python 81.33% Jupyter Notebook 18.62% Shell 0.05%
artificial-intelligence interpretability knowledge-editing large-language-models natural-language-processing knowledge-circuit circuit hallucination knowledge-edting model-editing

knowledgecircuits's People

Contributors

dependabot[bot] avatar littlefive5 avatar xeekee avatar zxlzr avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar

Forkers

sachab01

knowledgecircuits's Issues

Interpreting output model

Hi,

I ran your code and this gave me 100 circuits and a pickle file. I do not understand how I can detect from this which the best circuit is. Thanks!

How to analyse components for tinyllama?

When I run component.ipynb to analyse tinyllama, I encounter the following error:
transformer_lens/HookedTransformer.py", line 1838, in refactor_factored_attn_matrices self.cfg.positional_embedding_type != "rotary" AssertionError: You can't refactor the QK circuit when using rotary embeddings (as the QK matrix depends on the position of the query and key)

How should I analyse the experimental results of tinyllama? Thank you for your help.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.