Data

Tools

Indexes

Applications

Experiments

Open Source Science

transformer-attention

compare the theory attention gradient with PyTorch attention gradient

https://github.com/say-hello2y/transformer-attention

Science Score: 54.0%

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
    Links to: arxiv.org
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (4.4%) to scientific vocabulary
Last synced: 9 months ago · JSON representation ·

Repository

compare the theory attention gradient with PyTorch attention gradient

Basic Info
  • Host: GitHub
  • Owner: Say-Hello2y
  • Language: Python
  • Default Branch: main
  • Size: 8.79 KB
Statistics
  • Stars: 13
  • Watchers: 1
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Created almost 4 years ago · Last pushed about 2 years ago
Metadata Files
Readme Citation

README.md

Transformer-attention

The full derivation of Transformer gradient. compare the theory attention gradient with PyTorch attention gradient

  • If you want see the detail calcualtion,please see CN,EN

Citation

If you find this open source release useful, please cite in your paper: @software{He_The_full_derivation_2022, author = {He, Longxiang}, month = may, title = {{The full derivation of Transformer gradient}}, url = {https://github.com/Say-Hello2y/Transformer-attention.git}, version = {0.0.0}, year = {2022} }

Owner

  • Name: Longxiang he
  • Login: Say-Hello2y
  • Kind: user
  • Location: ShenZhen China
  • Company: Tsinghua SIGS

Tsinghua SIGS,ShenZhen,China

Citation (citation.cff) 

cff-version: 1.2.0
message: "If you think my work is useful, please cite it as below."
authors:
- family-names: "He"
  given-names: "Longxiang"
  orcid: "https://orcid.org/0009-0002-4904-8884"
title: "The full derivation of Transformer gradient"
version: 0.0.0
// doi: 10.5281/zenodo.1234
date-released: 2022-5-1
url: "https://github.com/Say-Hello2y/Transformer-attention.git"

GitHub Events

Total
  • Watch event: 3
  • Fork event: 1
Last Year
  • Watch event: 3
  • Fork event: 1