badtransformer

Simplified and easy-to-understand transformer

https://github.com/uefi-code/badtransformer

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Committers with academic emails
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (2.3%) to scientific vocabulary

Keywords

deep-learning natural-language-processing neural-networks pytorch transformer
Last synced: 6 months ago · JSON representation ·

Repository

Simplified and easy-to-understand transformer

Basic Info
  • Host: GitHub
  • Owner: UEFI-code
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 1010 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
deep-learning natural-language-processing neural-networks pytorch transformer
Created about 3 years ago · Last pushed 12 months ago
Metadata Files
Readme Citation

README.md

BadTransformer

BadTransformer is a simplified and easy-to-understand transformer proposed by Shizhuo Zhang. It simplifies the encoder and decoder structures and changes the multi-head attention mechanism to a single-head attention mechanism, while still potentially achieving the same effects as the original transformer.

Logo

Using Sence

...

Owner

  • Name: SuperHacker UEFI
  • Login: UEFI-code
  • Kind: user

Microsoft Learn Student Ambassador | Bionic Researcher | Software Engineer | BISTU

Citation (CITATION.cff)

cff-version: 2.0.0
message: If you use this model, please cite it as below.
title: BadTransformer
authors:
  - family-names: Zhang
    given-names: Shizhuo
  - family-names: BadTransformer Team
url: https://github.com/UEFI-code/BadTransformer
preferred-citation:
  type: neural network model
  title: "BadTransformer: An open-source project demonstrating a simplified transformer model."
  authors:
    - family-names: Zhang
      given-names: Shizhuo

GitHub Events

Total
  • Push event: 9
Last Year
  • Push event: 9

Committers

Last synced: 9 months ago

All Time
  • Total Commits: 30
  • Total Committers: 2
  • Avg Commits per committer: 15.0
  • Development Distribution Score (DDS): 0.4
Past Year
  • Commits: 5
  • Committers: 1
  • Avg Commits per committer: 5.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
UEFI-code z****g@h****m 18
UEFI-code 1****1@q****m 12
Committer Domains (Top 20 + Academic)
qq.com: 1