Giter Club home page Giter Club logo

Comments (5)

Minami-su avatar Minami-su commented on June 7, 2024

image
image

from llama-moe.

Spico197 avatar Spico197 commented on June 7, 2024

Hi there, thanks for your interest in this project~

inv_freq will be re-initialized from scratch each time when we initialize a model. This is NOT expected if you have fine-tuned or changed the inv_freq. In that case, this parameter should be in part of the dumpped model weights.

from llama-moe.

Minami-su avatar Minami-su commented on June 7, 2024

Hi there, thanks for your interest in this project~

inv_freq will be re-initialized from scratch each time when we initialize a model. This is NOT expected if you have fine-tuned or changed the inv_freq. In that case, this parameter should be in part of the dumpped model weights.

So, this error "" Some weights of LlamaMoEForCausalLM were not initialized" "has no effect?

from llama-moe.

Spico197 avatar Spico197 commented on June 7, 2024

There are no effects if you don't change this part of weights and could accept its re-initialization. I checked the model weights in Qwen/Qwen1.5-4B but found no inv_freq. So the re-initialization is a expected behaviour.

from llama-moe.

Minami-su avatar Minami-su commented on June 7, 2024

There are no effects if you don't change this part of weights and could accept its re-initialization. I checked the model weights in Qwen/Qwen1.5-4B but found no inv_freq. So the re-initialization is a expected behaviour.

Thank you very much. I see.

from llama-moe.

Related Issues (18)

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.