Light

trellixvulnteam / pytorch-pretrained-bert_annotation_2bfn Goto Github PK

View Code? Open in Web Editor NEW

This project forked from yongbowin/pytorch-pretrained-bert_annotation

0.0 0.0 0.0 292 KB

bert annotation, input and output for people from scratch, 代码注释, 有每一步的输入和输出, 适合初学者

License: Apache License 2.0

Shell 0.12% Python 23.41% Jupyter Notebook 76.44% Dockerfile 0.03%

pytorch-pretrained-bert_annotation_2bfn's Introduction

PyTorch Pretrained Bert Annotation

This BERT annotation repo is for my personal study.

The raw README of PyTorch Pretrained Bert is here.
A very nice PPT to help understanding.
Synthetic Self-Training PPT.

Arch

The BertModel and BertForMaskedLM arch.

BertModel Arch

BertEmbeddings
- word_embeddings: Embedding(30522, 768)
- position_embeddings: Embedding(512, 768)
- token_type_embeddings: Embedding(2, 768)
- LayerNorm: BertLayerNorm()
- dropout: Dropout(p=0.1)
BertEncoder
- BertLayer: (12 layers)
  - BertAttention
    - BertSelfAttention
      - query: Linear(in_features=768, out_features=768, bias=True)
      - key: Linear(in_features=768, out_features=768, bias=True)
      - value: Linear(in_features=768, out_features=768, bias=True)
      - dropout: Dropout(p=0.1)
    - BertSelfOutput
      - dense: Linear(in_features=768, out_features=768, bias=True)
      - LayerNorm: BertLayerNorm()
      - dropout: Dropout(p=0.1)
  - BertIntermediate
    - dense: Linear(in_features=768, out_features=3072, bias=True)
    - activation: gelu
  - BertOutput
    - dense: Linear(in_features=3072, out_features=768, bias=True)
    - LayerNorm: BertLayerNorm()
    - dropout: Dropout(p=0.1)
BertPooler
- dense: Linear(in_features=768, out_features=768, bias=True)
- activation: Tanh()

BertForMaskedLM Arch

BertModel
- BertEmbeddings
  - word_embeddings: Embedding(30522, 768)
  - position_embeddings: Embedding(512, 768)
  - token_type_embeddings: Embedding(2, 768)
  - LayerNorm: BertLayerNorm()
  - dropout: Dropout(p=0.1)
- BertEncoder
  - BertLayer: (12 layers)
    - BertAttention
      - BertSelfAttention
        
        query: Linear(in_features=768, out_features=768, bias=True)
        
        key: Linear(in_features=768, out_features=768, bias=True)
        
        value: Linear(in_features=768, out_features=768, bias=True)
        
        dropout: Dropout(p=0.1)
      - BertSelfOutput
        
        dense: Linear(in_features=768, out_features=768, bias=True)
        
        LayerNorm: BertLayerNorm()
        
        dropout: Dropout(p=0.1)
    - BertIntermediate
      - dense: Linear(in_features=768, out_features=3072, bias=True)
      - activation: gelu
    - BertOutput
      - dense: Linear(in_features=3072, out_features=768, bias=True)
      - LayerNorm: BertLayerNorm()
      - dropout: Dropout(p=0.1)
- BertPooler
  - dense: Linear(in_features=768, out_features=768, bias=True)
  - activation: Tanh()
BertOnlyMLMHead
- BertLMPredictionHead
  - transform: BertPredictionHeadTransform
    - dense: Linear(in_features=768, out_features=768, bias=True)
    - LayerNorm: BertLayerNorm()
  - decoder: Linear(in_features=768, out_features=30522, bias=False)

pytorch-pretrained-bert_annotation_2bfn's People

Contributors

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
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.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.