Code Monkey home page Code Monkey logo

Comments (6)

feizc avatar feizc commented on September 21, 2024 3

Hi, i have tried to fine-tune LLaMA model for better Chinese text generation.
Please refer to: https://github.com/feizc/MLE-LLaMA

from llama.

AISuperMa avatar AISuperMa commented on September 21, 2024 2

I have tested the Chinese support with the 7B model. Unfortunately, it seems the support of Chinese is extremely poor. (Perhaps increase the parameters can improve the performance in Chinese, but I have no ability to test)

I think if the vocab contains chinese character, it is fine, we can fine-tuning it, but if it doesn't, it is hard to us to do more research in chinese

from llama.

AISuperMa avatar AISuperMa commented on September 21, 2024

i have same question

from llama.

qwer10 avatar qwer10 commented on September 21, 2024

i have the same question too, in llama paper i could not find any zh corpus

from llama.

mnixry avatar mnixry commented on September 21, 2024

I have tested the Chinese support with the 7B model. Unfortunately, it seems the support of Chinese is extremely poor. (Perhaps increase the parameters can improve the performance in Chinese, but I have no ability to test)

from llama.

jspisak avatar jspisak commented on September 21, 2024

Closing this issues - Cool project @feizc !!

from llama.

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.