Giter Club home page Giter Club logo

torch.mingpt's Introduction

C# port of MinGPT - a simple deep learning transformer.

MinGPT on NuGet

Full training sample in the app folder.

Training with default parameters requires approximately 5.5GB of GPU memory + size of input file.

torch.mingpt's People

Contributors

lostmsu avatar

Stargazers

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

Watchers

 avatar  avatar  avatar

torch.mingpt's Issues

Overfitting

I have a dataset with 10 000 lines of text.

The data inside is code and is in this format:

nameofskill:
Skills:

  • effect:particles{etc=random} @target

the first line changes depending on the name of the skill,
the second line never changes.
The third line changes and is different for each different skill.

The issue is that when I train the model, whatever is the name of the skill, the following lines after the Skills line are always the same.

for example:

fireskill:
Skills:

  • flame

waterskill:
Skills:

  • flame

rockskill:
Skills:

  • flame

it doesnt seems to undertsand what is written ,and changing the temperature to 0.7 does nothing to help. It always output the same data.

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.