A python library for highly configurable transformers - easing model architecture search and experimentation.

Related tags

Deep Learningdeep-learningtransformerspytorchartificial-intelligence
Overview

configaformers (re-factor in progress)

A python library for highly configurable transformers - easing model architecture search and experimentation. It is premised on building small and independent modules that enables users to configure custom transformer architectures.

Special thanks to lucidrains (https://github.com/lucidrains) and Kharr.

Usage

Quick demo that will configure a 768-wide, 12-layer transformer, with a language modeling head.

Import, and create token embedding block:

import torch
from model_builder import ConfigaFormer

emb = []
model_dim = 768

emb.append({'type': 'embedding',
            'output_dim': model_dim,
            'num_classes': 50257})

Create self-attention module:

attn = []

# Make residual and norm
attn.append({'type': 'make_stream', 'output_name': 'residual'})
attn.append({'type': 'norm', 'norm_type': 'layer_norm'})

# Make QKVs
attn.append({'type': 'linear', 'output_name': 'queries'})
attn.append({'type': 'linear', 'output_name': 'keys'})
attn.append({'type': 'linear', 'output_name': 'values'})

attn.append({'type': 'make_heads', 'input_name': 'queries', 'output_name': 'queries', 'num_heads': 12})
attn.append({'type': 'make_heads', 'input_name': 'keys', 'output_name': 'keys', 'num_heads': 12})

attn.append({'type': 'rope', 'input_name': 'queries', 'output_name': 'queries', 'rotate_dim': 16})
attn.append({'type': 'rope', 'input_name': 'keys', 'output_name': 'keys', 'rotate_dim': 16})

# Perform attention
attn.append({'type': 'mha_dots',
             'input_name_queries': 'queries',
             'input_name_keys': 'keys'})
attn.append({'type': 'attention_offset'})
attn.append({'type': 'mha_sum',
             'input_name_values': 'values'})

# Mix
attn.append({'type': 'linear'})

# Add residual
attn.append({'type': 'merge_streams',
             'input_name_1': 'residual',
             'merge_type': 'add'})

Create FFN module:

ffn = []

# Make residual and norm
ffn.append({'type': 'make_stream', 'output_name': 'residual'})
ffn.append({'type': 'norm', 'norm_type': 'layer_norm'})

# Proj Up
ffn.append({'type': 'linear', 'output_dim': 768*4})

# Activation
ffn.append({'type': 'activation'})

# Proj Down
ffn.append({'type': 'linear', 'output_dim': 768})

# Add residual
ffn.append({'type': 'merge_streams',
             'input_name_1': 'residual',
             'merge_type': 'add'})

Create language modeling head:

to_logits = []
to_logits.append({'type': 'linear', 'output_dim': 50257})

Create blocks, initialize input shapes, and init the model:

transformer_block = attn + ffn
classifier = ffn + to_logits

blocks = [{"config": emb,
           "repeat": 1},
          {"config": transformer_block,
           "repeat": 12},
          {"config": classifier,
           "repeat": 1},
          ]
          
my_config = {'blocks' = blocks}
input_streams = {'emb_ids': ['B', 'L_in'],
                 'attn_offset': ['B', 12, 'L_in', 'L_in'],}

model = ConfigaFormer(model_config=my_config,
                     input_streams=input_streams).cuda()

This will print out the transformer config:

Block #1, 1x
embedding -> Input(s): emb_ids (BSZ, L_in) - Output(s): x (BSZ, L_in, 768)


Block #2, 12x
make_stream -> Input(s): x (BSZ, L_in, 768) - Output(s): residual (BSZ, L_in, 768)
norm -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): queries (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): keys (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): values (BSZ, L_in, 768)
make_heads -> Input(s): queries (BSZ, L_in, 768) - Output(s): queries (BSZ, 12, L_in, 64)
make_heads -> Input(s): keys (BSZ, L_in, 768) - Output(s): keys (BSZ, 12, L_in, 64)
rope -> Input(s): queries (BSZ, 12, L_in, 64), rope_16 (2048, 16) - Output(s): queries (BSZ, 12, L_in, 64)
rope -> Input(s): keys (BSZ, 12, L_in, 64), rope_16 (2048, 16) - Output(s): keys (BSZ, 12, L_in, 64)
mha_dots -> Input(s): queries (BSZ, 12, L_in, 64), keys (BSZ, 12, L_in, 64) - Output(s): attn_dots (BSZ, 12, L_in, L_in)
attention_offset -> Input(s): attn_dots (BSZ, 12, L_in, L_in), attn_offset (BSZ, 12, L_in, L_in) - Output(s): attn_dots (BSZ, 12, L_in, L_in)
mha_sum -> Input(s): values (BSZ, L_in, 768), attn_dots (BSZ, 12, L_in, L_in) - Output(s): x (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
merge_streams -> Input(s): residual (BSZ, L_in, 768), x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
make_stream -> Input(s): x (BSZ, L_in, 768) - Output(s): residual (BSZ, L_in, 768)
norm -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 3072)
activation -> Input(s): x (BSZ, L_in, 3072) - Output(s): x (BSZ, L_in, 3072)
linear -> Input(s): x (BSZ, L_in, 3072) - Output(s): x (BSZ, L_in, 768)
merge_streams -> Input(s): residual (BSZ, L_in, 768), x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)


Block #3, 1x
make_stream -> Input(s): x (BSZ, L_in, 768) - Output(s): residual (BSZ, L_in, 768)
norm -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 3072)
activation -> Input(s): x (BSZ, L_in, 3072) - Output(s): x (BSZ, L_in, 3072)
linear -> Input(s): x (BSZ, L_in, 3072) - Output(s): x (BSZ, L_in, 768)
merge_streams -> Input(s): residual (BSZ, L_in, 768), x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 50257)

Before running, we need to get the attention offset (in this case, AliBi with a causal mask):

from attention_offset_module import get_alibi

attn_offset = get_alibi(num_heads=12)

Now we can use the model:

input_data = {'emb_ids': batch_ids.view(bsz, 1024).cuda(),
              'attn_offset': attn_offset.cuda()}

logits = model(input_data)['x'].view(bsz, 1024, 50257)

TODO

  1. Token shifting, down/up sampling
  2. Create higher abstractions for FFN and self-attention
  3. everything else
Owner
Anthony Fuller
Anthony Fuller
GitHub Repository
This program was designed to detect whether someone is wearing a facemask through a live video stream.

This program was designed to detect whether someone is wearing a facemask through a live video stream. A custom lightweight CNN trained with TensorFlow on a public dataset provided by Kaggle is used

0 Apr 02, 2022
A large-scale video dataset for the training and evaluation of 3D human pose estimation models

ASPset-510 ASPset-510 (Australian Sports Pose Dataset) is a large-scale video dataset for the training and evaluation of 3D human pose estimation mode

Aiden Nibali 36 Oct 30, 2022
Fast algorithms to compute an approximation of the minimal volume oriented bounding box of a point cloud in 3D.

ApproxMVBB Status Build UnitTests Homepage Fast algorithms to compute an approximation of the minimal volume oriented bounding box of a point cloud in

Gabriel Nützi 390 Dec 31, 2022
Hierarchical Memory Matching Network for Video Object Segmentation (ICCV 2021)

Hierarchical Memory Matching Network for Video Object Segmentation Hongje Seong, Seoung Wug Oh, Joon-Young Lee, Seongwon Lee, Suhyeon Lee, Euntai Kim

Hongje Seong 72 Dec 14, 2022
WSDM‘2022: Knowledge Enhanced Sports Game Summarization

Knowledge Enhanced Sports Game Summarization Cooming Soon! :) Data will be released after approval process. Code will be published once the author of

Jiaan Wang 14 Jul 13, 2022
《K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters》(2020)

K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters This repository is the implementation of the paper "K-Adapter: Infusing Knowledge

Microsoft 118 Dec 13, 2022
Quantile Regression DQN a Minimal Working Example, Distributional Reinforcement Learning with Quantile Regression

Quantile Regression DQN Quantile Regression DQN a Minimal Working Example, Distributional Reinforcement Learning with Quantile Regression (https://arx

Arsenii Senya Ashukha 80 Sep 17, 2022
DeepConsensus uses gap-aware sequence transformers to correct errors in Pacific Biosciences (PacBio) Circular Consensus Sequencing (CCS) data.

DeepConsensus DeepConsensus uses gap-aware sequence transformers to correct errors in Pacific Biosciences (PacBio) Circular Consensus Sequencing (CCS)

Google 149 Dec 19, 2022
Source code and dataset for ACL2021 paper: "ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learning".

ERICA Source code and dataset for ACL2021 paper: "ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive L

THUNLP 75 Nov 02, 2022
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis Jungil Kong, Jaehyeon Kim, Jaekyoung Bae In our paper, we p

Rishikesh (ऋषिकेश) 31 Dec 08, 2022
Citation Intent Classification in scientific papers using the Scicite dataset an Pytorch

Citation Intent Classification Table of Contents About the Project Built With Installation Usage Acknowledgments About The Project Citation Intent Cla

Federico Nocentini 4 Mar 04, 2022
PyTorch implementation of the paper: "Preference-Adaptive Meta-Learning for Cold-Start Recommendation", IJCAI, 2021.

PAML PyTorch implementation of the paper: "Preference-Adaptive Meta-Learning for Cold-Start Recommendation", IJCAI, 2021. (Continuously updating ) Int

15 Nov 18, 2022
Code for ICML 2021 paper: How could Neural Networks understand Programs?

OSCAR This repository contains the source code of our ICML 2021 paper How could Neural Networks understand Programs?. Environment Run following comman

Dinglan Peng 115 Dec 17, 2022
Convolutional Neural Network to detect deforestation in the Amazon Rainforest

Convolutional Neural Network to detect deforestation in the Amazon Rainforest This project is part of my final work as an Aerospace Engineering studen

5 Feb 17, 2022
Training vision models with full-batch gradient descent and regularization

Stochastic Training is Not Necessary for Generalization -- Training competitive vision models without stochasticity This repository implements trainin

Jonas Geiping 32 Jan 06, 2023
Pytorch implementation of "Get To The Point: Summarization with Pointer-Generator Networks"

About this repository This repo contains an Pytorch implementation for the ACL 2017 paper Get To The Point: Summarization with Pointer-Generator Netwo

wxDai 7 Oct 14, 2022
Apply our monocular depth boosting to your own network!

MergeNet - Boost Your Own Depth Boost custom or edited monocular depth maps using MergeNet Input Original result After manual editing of base You can

Computational Photography Lab @ SFU 142 Dec 17, 2022
Algorithm to texture 3D reconstructions from multi-view stereo images

MVS-Texturing Welcome to our project that textures 3D reconstructions from images. This project focuses on 3D reconstructions generated using structur

Nils Moehrle 766 Jan 04, 2023
Implementation of our recent paper, WOOD: Wasserstein-based Out-of-Distribution Detection.

WOOD Implementation of our recent paper, WOOD: Wasserstein-based Out-of-Distribution Detection. Abstract The training and test data for deep-neural-ne

8 Dec 24, 2022
Social Network Ads Prediction

Social network advertising, also social media targeting, is a group of terms that are used to describe forms of online advertising that focus on social networking services.

Khazar 2 Jan 28, 2022