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
Annotate with anyone, anywhere.

h h is the web app that serves most of the https://hypothes.is/ website, including the web annotations API at https://hypothes.is/api/. The Hypothesis

Hypothesis 2.6k Jan 08, 2023
Trading environnement for RL agents, backtesting and training.

TradzQAI Trading environnement for RL agents, backtesting and training. Live session with coinbasepro-python is finaly arrived ! Available sessions: L

Tony Denion 164 Oct 30, 2022
Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks

Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks This repository contains a TensorFlow implementation of "

Jingwei Zheng 5 Jan 08, 2023
A modular, research-friendly framework for high-performance and inference of sequence models at many scales

T5X T5X is a modular, composable, research-friendly framework for high-performance, configurable, self-service training, evaluation, and inference of

Google Research 1.1k Jan 08, 2023
This Repo is the official CUDA implementation of ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures

Introduction This Repo is the official CUDA implementation of ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures. @inproceedings{Wa

Jiaqi Wang 42 Jan 07, 2023
Implementation of StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation in PyTorch

StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation Implementation of StyleSpace Analysis: Disentangled Controls for StyleGAN Ima

Xuanchi Ren 86 Dec 07, 2022
This repo contains the implementation of the algorithm proposed in Off-Belief Learning, ICML 2021.

Off-Belief Learning Introduction This repo contains the implementation of the algorithm proposed in Off-Belief Learning, ICML 2021. Environment Setup

Facebook Research 32 Jan 05, 2023
code for generating data set ES-ImageNet with corresponding training code

es-imagenet-master code for generating data set ES-ImageNet with corresponding training code dataset generator some codes of ODG algorithm The variabl

Ordinarabbit 18 Dec 25, 2022
Implementation of Fast Transformer in Pytorch

Fast Transformer - Pytorch Implementation of Fast Transformer in Pytorch. This only work as an encoder. Yannic video AI Epiphany Install $ pip install

Phil Wang 167 Dec 27, 2022
PyTorch implementations of the paper: "DR.VIC: Decomposition and Reasoning for Video Individual Counting, CVPR, 2022"

DRNet for Video Indvidual Counting (CVPR 2022) Introduction This is the official PyTorch implementation of paper: DR.VIC: Decomposition and Reasoning

tao han 35 Nov 22, 2022
Minimal implementation of PAWS (https://arxiv.org/abs/2104.13963) in TensorFlow.

PAWS-TF 🐾 Implementation of Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples (PAWS)

Sayak Paul 43 Jan 08, 2023
Explaining neural decisions contrastively to alternative decisions.

Contrastive Explanations for Model Interpretability This is the repository for the paper "Contrastive Explanations for Model Interpretability", about

AI2 16 Oct 16, 2022
PyTorch Implementation for Fracture Detection in Wrist Bone X-ray Images

wrist-d PyTorch Implementation for Fracture Detection in Wrist Bone X-ray Images note: Paper: Under Review at MPDI Diagnostics Submission Date: Novemb

Fatih UYSAL 5 Oct 12, 2022
Do Neural Networks for Segmentation Understand Insideness?

This is part of the code to reproduce the results of the paper Do Neural Networks for Segmentation Understand Insideness? [pdf] by K. Villalobos (*),

biolins 0 Mar 20, 2021
Source Code for AAAI 2022 paper "Graph Convolutional Networks with Dual Message Passing for Subgraph Isomorphism Counting and Matching"

Graph Convolutional Networks with Dual Message Passing for Subgraph Isomorphism Counting and Matching This repository is an official implementation of

HKUST-KnowComp 13 Sep 08, 2022
TensorFlow implementation of the paper "Hierarchical Attention Networks for Document Classification"

Hierarchical Attention Networks for Document Classification This is an implementation of the paper Hierarchical Attention Networks for Document Classi

Quoc-Tuan Truong 83 Dec 05, 2022
SpanNER: Named EntityRe-/Recognition as Span Prediction

SpanNER: Named EntityRe-/Recognition as Span Prediction Overview | Demo | Installation | Preprocessing | Prepare Models | Running | System Combination

NeuLab 104 Dec 17, 2022
Easily pull telemetry data and create beautiful visualizations for analysis.

This repository is a work in progress. Anything and everything is subject to change. Porpo Table of Contents Porpo Table of Contents General Informati

Ryan Dawes 33 Nov 30, 2022
Revisiting Global Statistics Aggregation for Improving Image Restoration

Revisiting Global Statistics Aggregation for Improving Image Restoration Xiaojie Chu, Liangyu Chen, Chengpeng Chen, Xin Lu Paper: https://arxiv.org/pd

MEGVII Research 128 Dec 24, 2022
A tool to visualise the results of AlphaFold2 and inspect the quality of structural predictions

AlphaFold Analyser This program produces high quality visualisations of predicted structures produced by AlphaFold. These visualisations allow the use

Oliver Powell 3 Nov 13, 2022