Code Monkey home page Code Monkey logo

Comments (2)

bstadt avatar bstadt commented on June 6, 2024

I wonder if this exists in the training data:
https://atlas.nomic.ai/map/gpt4all_data_clean_without_p3

if you can identify a query or subset that has this property, we will exclude it from the next train

from gpt4all.

michael-quinlan avatar michael-quinlan commented on June 6, 2024

I think this is happening in lora training. I saw a similar issue tloen/alpaca-lora#110 and I did some fine-tuning myself with some custom data (on the alpaca-lora code) and I saw the exact behavior you see here of generating formated instructions. I know i'm bringing issues from cross repo but the fact this exsits in multiple implementations must mean something.

from gpt4all.

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.