Git Product home page Git Product logo

Comments (2)

xiamengzhou avatar xiamengzhou commented on August 20, 2024

Given how hidden_z is modeled (with hard concrete distributions), it's essentially learning a discrete binary value of 1 (retain the dimension) or 0 (prune the dimension). As the values strictly fall in side [0, 1], I don't think it will cause gradient explosion issues. For the same reason, it should not have an influence on the magnitude of the last hidden state. Let me know if it is clear!

from llm-shearing.

sbwww avatar sbwww commented on August 20, 2024

As the values strictly fall in side [0, 1]

Yes, the hidden state won't be too large, but will it be too small? Just plan to check it on the model without re-training.

from llm-shearing.

Related Issues (20)

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    🖖 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. 📊📈🎉

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 ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.