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
Local trajectory planner based on a multilayer graph framework for autonomous race vehicles.

Graph-Based Local Trajectory Planner The graph-based local trajectory planner is python-based and comes with open interfaces as well as debug, visuali

TUM - Institute of Automotive Technology 160 Jan 04, 2023
Hand Gesture Volume Control is AIML based project which uses image processing to control the volume of your Computer.

Hand Gesture Volume Control Modules There are basically three modules Handtracking Program Handtracking Module Volume Control Program Handtracking Pro

VITTAL 1 Jan 12, 2022
Deep learning PyTorch library for time series forecasting, classification, and anomaly detection

Deep learning for time series forecasting Flow forecast is an open-source deep learning for time series forecasting framework. It provides all the lat

AIStream 1.2k Jan 04, 2023
Planning from Pixels in Environments with Combinatorially Hard Search Spaces -- NeurIPS 2021

PPGS: Planning from Pixels in Environments with Combinatorially Hard Search Spaces Environment Setup We recommend pipenv for creating and managing vir

Autonomous Learning Group 11 Jun 26, 2022
SubOmiEmbed: Self-supervised Representation Learning of Multi-omics Data for Cancer Type Classification

SubOmiEmbed: Self-supervised Representation Learning of Multi-omics Data for Cancer Type Classification

Sayed Hashim 3 Nov 15, 2022
Python interface for the DIGIT tactile sensor

DIGIT-INTERFACE Python interface for the DIGIT tactile sensor. For updates and discussions please join the #DIGIT channel at the www.touch-sensing.org

Facebook Research 35 Dec 22, 2022
Pywonderland - A tour in the wonderland of math with python.

A Tour in the Wonderland of Math with Python A collection of python scripts for drawing beautiful figures and animating interesting algorithms in math

Zhao Liang 4.1k Jan 03, 2023
Concept drift monitoring for HA model servers.

{Fast, Correct, Simple} - pick three Easily compare training and production ML data & model distributions Goals Boxkite is an instrumentation library

98 Dec 15, 2022
Pytorch implementation for A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose

A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose Paper | Website | Data A-NeRF: Articulated Neural Radiance F

Shih-Yang Su 172 Dec 22, 2022
Code accompanying the paper "How Tight Can PAC-Bayes be in the Small Data Regime?"

How Tight Can PAC-Bayes be in the Small Data Regime? This is the code to reproduce all experiments for the following paper: @inproceedings{Foong:2021:

5 Dec 21, 2021
BOOKSUM: A Collection of Datasets for Long-form Narrative Summarization

BOOKSUM: A Collection of Datasets for Long-form Narrative Summarization Authors: Wojciech Kryściński, Nazneen Rajani, Divyansh Agarwal, Caiming Xiong,

Salesforce 125 Dec 31, 2022
Certifiable Outlier-Robust Geometric Perception

Certifiable Outlier-Robust Geometric Perception About This repository holds the implementation for certifiably solving outlier-robust geometric percep

83 Dec 31, 2022
Official PyTorch implementation of MAAD: A Model and Dataset for Attended Awareness

MAAD: A Model for Attended Awareness in Driving Install // Datasets // Training // Experiments // Analysis // License Official PyTorch implementation

7 Oct 16, 2022
ByteTrack: Multi-Object Tracking by Associating Every Detection Box

ByteTrack ByteTrack is a simple, fast and strong multi-object tracker. ByteTrack: Multi-Object Tracking by Associating Every Detection Box Yifu Zhang,

Yifu Zhang 2.9k Jan 04, 2023
FAMIE is a comprehensive and efficient active learning (AL) toolkit for multilingual information extraction (IE)

FAMIE: A Fast Active Learning Framework for Multilingual Information Extraction

18 Sep 01, 2022
Easy way to add GoogleMaps to Flask applications. maintainer: @getcake

Flask Google Maps Easy to use Google Maps in your Flask application requires Jinja Flask A google api key get here Contribute To contribute with the p

Flask Extensions 611 Dec 05, 2022
Fast Differentiable Matrix Sqrt Root

Fast Differentiable Matrix Sqrt Root Geometric Interpretation of Matrix Square Root and Inverse Square Root This repository constains the official Pyt

YueSong 42 Dec 30, 2022
These are the materials for the paper "Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations"

Few-shot-NLEs These are the materials for the paper "Few-Shot Out-of-Domain Transfer Learning of Natural Language Explanations". You can find the smal

Yordan Yordanov 0 Oct 21, 2022
This is the solution for 2nd rank in Kaggle competition: Feedback Prize - Evaluating Student Writing.

Feedback Prize - Evaluating Student Writing This is the solution for 2nd rank in Kaggle competition: Feedback Prize - Evaluating Student Writing. The

Udbhav Bamba 41 Dec 14, 2022
PyTorch implementation of paper "Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes", CVPR 2021

Neural Scene Flow Fields PyTorch implementation of paper "Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes", CVPR 20

Zhengqi Li 585 Jan 04, 2023