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
Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis Implementation

Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis Implementation This project attempted to implement the paper Putting NeRF on a

254 Dec 27, 2022
ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction

ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction. NeurIPS 2021.

Gengshan Yang 59 Nov 25, 2022
SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021)

SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data (AAAI 2021) PyTorch implementation of SnapMix | paper Method Overview Cite

DavidHuang 126 Dec 30, 2022
Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Networks

CyGNet This repository reproduces the AAAI'21 paper “Learning from History: Modeling Temporal Knowledge Graphs with Sequential Copy-Generation Network

CunchaoZ 89 Jan 03, 2023
In this project I played with mlflow, streamlit and fastapi to create a training and prediction app on digits

Fastapi + MLflow + streamlit Setup env. I hope I covered all. pip install -r requirements.txt Start app Go in the root dir and run these Streamlit str

76 Nov 23, 2022
Domain Adaptation with Invariant RepresentationLearning: What Transformations to Learn?

Domain Adaptation with Invariant RepresentationLearning: What Transformations to Learn? Repository Structure: DSAN |└───amazon |    └── dataset (Amazo

DMIRLAB 17 Jan 04, 2023
Towhee is a flexible machine learning framework currently focused on computing deep learning embeddings over unstructured data.

Towhee is a flexible machine learning framework currently focused on computing deep learning embeddings over unstructured data.

1.7k Jan 08, 2023
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Introduction This is a Python package available on PyPI for NVIDIA-maintained utilities to streamline mixed precision and distributed training in Pyto

Artit 'Art' Wangperawong 5 Sep 29, 2021
Package towards building Explainable Forecasting and Nowcasting Models with State-of-the-art Deep Neural Networks and Dynamic Factor Model on Time Series data sets with single line of code. Also, provides utilify facility for time-series signal similarities matching, and removing noise from timeseries signals.

DeepXF: Explainable Forecasting and Nowcasting with State-of-the-art Deep Neural Networks and Dynamic Factor Model Also, verify TS signal similarities

AjayAru 88 Dec 27, 2022
Deploy a ML inference service on a budget in less than 10 lines of code.

BudgetML is perfect for practitioners who would like to quickly deploy their models to an endpoint, but not waste a lot of time, money, and effort trying to figure out how to do this end-to-end.

1.3k Dec 25, 2022
TransGAN: Two Transformers Can Make One Strong GAN

[Preprint] "TransGAN: Two Transformers Can Make One Strong GAN", Yifan Jiang, Shiyu Chang, Zhangyang Wang

VITA 1.5k Jan 07, 2023
A PyTorch implementation of "SimGNN: A Neural Network Approach to Fast Graph Similarity Computation" (WSDM 2019).

SimGNN ⠀⠀⠀ A PyTorch implementation of SimGNN: A Neural Network Approach to Fast Graph Similarity Computation (WSDM 2019). Abstract Graph similarity s

Benedek Rozemberczki 534 Dec 25, 2022
Voila - Voilà turns Jupyter notebooks into standalone web applications

Rendering of live Jupyter notebooks with interactive widgets. Introduction Voilà turns Jupyter notebooks into standalone web applications. Unlike the

Voilà Dashboards 4.5k Jan 03, 2023
MultiTaskLearning - Multi Task Learning for 3D segmentation

Multi Task Learning for 3D segmentation Perception stack of an Autonomous Drivin

2 Sep 22, 2022
This is an (re-)implementation of DeepLab-ResNet in TensorFlow for semantic image segmentation on the PASCAL VOC dataset.

DeepLab-ResNet-TensorFlow This is an (re-)implementation of DeepLab-ResNet in TensorFlow for semantic image segmentation on the PASCAL VOC dataset. Up

19 Jan 16, 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
An LSTM based GAN for Human motion synthesis

GAN-motion-Prediction An LSTM based GAN for motion synthesis has a few issues reading H3.6M data from A.Jain et al , will fix soon. Prediction of the

Amogh Adishesha 9 Jun 17, 2022
Finite Element Analysis

FElupe - Finite Element Analysis FElupe is a Python 3.6+ finite element analysis package focussing on the formulation and numerical solution of nonlin

Andreas D. 20 Jan 09, 2023
Facial Image Inpainting with Semantic Control

Facial Image Inpainting with Semantic Control In this repo, we provide a model for the controllable facial image inpainting task. This model enables u

Ren Yurui 8 Nov 22, 2021
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