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
HNN: Human (Hollywood) Neural Network

HNN: Human (Hollywood) Neural Network Learn the top 1000 actors on IMDB with your very own low cost, highly parallel, CUDAless biological neural netwo

Madhava Jay 0 Dec 21, 2021
Code for "Single-view robot pose and joint angle estimation via render & compare", CVPR 2021 (Oral).

Single-view robot pose and joint angle estimation via render & compare Yann Labbé, Justin Carpentier, Mathieu Aubry, Josef Sivic CVPR: Conference on C

Yann Labbé 51 Oct 14, 2022
diablo2 resurrected loot filter

Only For Chinese and Traditional Chinese The filter only for Chinese and Traditional Chinese, i didn't change it for other language.Maybe you could mo

elmagnifico 249 Dec 04, 2022
Towards Interpretable Deep Metric Learning with Structural Matching

DIML Created by Wenliang Zhao*, Yongming Rao*, Ziyi Wang, Jiwen Lu, Jie Zhou This repository contains PyTorch implementation for paper Towards Interpr

Wenliang Zhao 75 Nov 11, 2022
Deep Learning Visuals contains 215 unique images divided in 23 categories

Deep Learning Visuals contains 215 unique images divided in 23 categories (some images may appear in more than one category). All the images were originally published in my book "Deep Learning with P

Daniel Voigt Godoy 1.3k Dec 28, 2022
Code for HodgeNet: Learning Spectral Geometry on Triangle Meshes, in SIGGRAPH 2021.

HodgeNet | Webpage | Paper | Video HodgeNet: Learning Spectral Geometry on Triangle Meshes Dmitriy Smirnov, Justin Solomon SIGGRAPH 2021 Set-up To ins

Dima Smirnov 61 Nov 27, 2022
CS506-Spring2022 - Code and Slides for Boston University CS 506

CS 506 - Computational Tools for Data Science Code, slides, and notes for Boston

Lance Galletti 17 May 06, 2022
Apache Spark - A unified analytics engine for large-scale data processing

Apache Spark Spark is a unified analytics engine for large-scale data processing. It provides high-level APIs in Scala, Java, Python, and R, and an op

The Apache Software Foundation 34.7k Jan 04, 2023
A PyTorch implementation of the Transformer model in "Attention is All You Need".

Attention is all you need: A Pytorch Implementation This is a PyTorch implementation of the Transformer model in "Attention is All You Need" (Ashish V

Yu-Hsiang Huang 7.1k Jan 04, 2023
Scales, Chords, and Cadences: Practical Music Theory for MIR Researchers

ISMIR-musicTheoryTutorial This repository has slides and Jupyter notebooks for the ISMIR 2021 tutorial Scales, Chords, and Cadences: Practical Music T

Johanna Devaney 58 Oct 11, 2022
A GUI for Face Recognition, based upon Docker, Tkinter, GPU and a camera device.

Face Recognition GUI This repository is a GUI version of Face Recognition by Adam Geitgey, where e.g. Docker and Tkinter are utilized. All the materia

Kasper Henriksen 6 Dec 05, 2022
[CVPR'21] Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild

IVOS-W Paper Learning to Recommend Frame for Interactive Video Object Segmentation in the Wild Zhaoyun Yin, Jia Zheng, Weixin Luo, Shenhan Qian, Hanli

SVIP Lab 38 Dec 12, 2022
My implementation of transformers related papers for computer vision in pytorch

vision_transformers This is my personnal repo to implement new transofrmers based and other computer vision DL models I am currenlty working without a

samsja 1 Nov 10, 2021
This repository contains the exercises and its solution contained in the book "An Introduction to Statistical Learning" in python.

An-Introduction-to-Statistical-Learning This repository contains the exercises and its solution contained in the book An Introduction to Statistical L

2.1k Jan 02, 2023
BasicNeuralNetwork - This project looks over the basic structure of a neural network and how machine learning training algorithms work

BasicNeuralNetwork - This project looks over the basic structure of a neural network and how machine learning training algorithms work. For this project, I used the sigmoid function as an activation

Manas Bommakanti 1 Jan 22, 2022
retweet 4 satoshi ⚡️

rt4sat retweet 4 satoshi This bot is the codebase for https://twitter.com/rt4sat please feel free to create an issue if you saw any bugs basically thi

6 Sep 30, 2022
(NeurIPS 2021) Realistic Evaluation of Transductive Few-Shot Learning

Realistic evaluation of transductive few-shot learning Introduction This repo contains the code for our NeurIPS 2021 submitted paper "Realistic evalua

Olivier Veilleux 14 Dec 13, 2022
To model the probability of a soccer coach leave his/her team during Campeonato Brasileiro for 10 chosen teams and considering years 2018, 2019 and 2020.

To model the probability of a soccer coach leave his/her team during Campeonato Brasileiro for 10 chosen teams and considering years 2018, 2019 and 2020.

Larissa Sayuri Futino Castro dos Santos 1 Jan 20, 2022
[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime

[Open Source]. The improved version of AnimeGAN. Landscape photos/videos to anime

CC 4.4k Dec 27, 2022
StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation

StyleGAN2 with adaptive discriminator augmentation (ADA) — Official TensorFlow implementation Training Generative Adversarial Networks with Limited Da

NVIDIA Research Projects 1.7k Dec 29, 2022