Explore extreme compression for pre-trained language models

Last update: Nov 14, 2022

Related tags

Deep Learning Xcompression

Overview

Explore extreme compression for pre-trained language models

Code for paper "Exploring extreme parameter compression for pre-trained language models ICLR2022"

Before Training

install some libraries

 pip install tensorly==0.5.0

Torch is needed, torch 1.0-1.4 is preferred

Install horovod for distributed learning

Configuration Install horovod on GPU

pip install horovod[pytorch]

loading pre-trained models

wget https://huggingface.co/bert-base-uncased/resolve/main/pytorch_model.bin -P  models/bert-base-uncased
wget https://huggingface.co/bert-base-uncased/resolve/main/vocab.txt -P  models/bert-base-uncased
cp models/bert-base-uncased/pytorch_model.bin models/bert-td-72-384/pytorch_model.bin 
cp models/bert-base-uncased/vocab.txt models/bert-td-72-384/vocab.txt

generate training data for given corpora (e.g., saved in the path "corpora" )

python pregenerate_training_data.py --train_corpus ${CORPUS_RAW} \ 
                  --bert_model ${BERT_BASE_DIR}$ \
                  --reduce_memory --do_lower_case \
                  --epochs_to_generate 3 \
                  --output_dir ${CORPUS_JSON_DIR}$

task data augmentation

python data_augmentation.py --pretrained_bert_model ${BERT_BASE_DIR}$ \
                            --glove_embs ${GLOVE_EMB}$ \
                            --glue_dir ${GLUE_DIR}$ \  
                            --task_name ${TASK_NAME}$

Decomposing BERT

decomposition and general distillation

Run with horovod

mpirun -np 8 -bind-to none -map-by slot -x NCCL_DEBUG=INFO -x LD_LIBRARY_PATH -x PATH -mca pml ob1 -mca btl ^openib python3 general_distill.py --teacher_model models/bert-base-uncased --student_model models/bert-gd-72-384 --pregenerated_data data/pregenerated_data --num_train_epochs 2.0 --train_batch_size 32 --output_dir output/bert-gd-72-384 -use_swap --do_lower_case

To restrict sharing among SAN or FFN, add "ops" and set "ops" to be "san" or "ffn" in bert-gd-72-384/config.json

ops = "san"

Evaluation

Task distillation with data augmentation in fine-tuning phase

Rename a pretrained model as "", for instance, change step_0_pytorch_model.bin to pytorch_model.bin, and change load_compressed_model from false to true in output/config.json

Task distillation for distributed training

CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 python -m torch.distributed.launch --nproc_per_node=8 task_distill.py --teacher_model models/bert-base-uncasedi/STS-B --student_model models/bert-gd-72-384 --task_name STS-B --aug_train --data_dir data/glue_data/SST-2 --max_seq_length 128 --train_batch_size 32 --aug_train --learning_rate 2e-5 --num_train_epochs 3.0 --output_dir ./output/36-256-STS-B

Task distillation for single gpu

python3  task_distill.py  --teacher_model models/bert-base-uncased   --student_model  models/bert-td-72-384  --output output_demo  --data_dir  data/glue_data/SST-2   --task_name  SST-2  --do_lower_case --aug_train

For augmentation, you should add --aug_train

Get test result for model

python run_glue.py --model_name_or_path  models/bert-td-72-384/SST-2 --task_name SST-2 --do_eval --do_predict --data_dir data/glue_data/STS-B --max_seq_length 128 --save_steps 500 --save_total_limit 2 --output_dir ./output/SST-2

Explore extreme compression for pre-trained language models

Related tags

Overview

Explore extreme compression for pre-trained language models

Before Training

install some libraries

loading pre-trained models

generate training data for given corpora (e.g., saved in the path "corpora" )

task data augmentation

Decomposing BERT

decomposition and general distillation

Evaluation

Task distillation with data augmentation in fine-tuning phase

Owner

twinkle

Raindrop strategy for Irregular time series

A curated list of the latest breakthroughs in AI (in 2021) by release date with a clear video explanation, link to a more in-depth article, and code.

Implementation of MeMOT - Multi-Object Tracking with Memory - in Pytorch

A PyTorch implementation of "Capsule Graph Neural Network" (ICLR 2019).

Brax is a differentiable physics engine that simulates environments made up of rigid bodies, joints, and actuators

Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.

Implementation of CVPR'21: RfD-Net: Point Scene Understanding by Semantic Instance Reconstruction

RuDOLPH: One Hyper-Modal Transformer can be creative as DALL-E and smart as CLIP

A PyTorch implementation of Sharpness-Aware Minimization for Efficiently Improving Generalization

Based on the given clinical dataset, Predict whether the patient having Heart Disease or Not having Heart Disease

Asymmetric Bilateral Motion Estimation for Video Frame Interpolation, ICCV2021

This is a vision-based 3d model manipulation and control UI

The official repository for our paper "The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers". We significantly improve the systematic generalization of transformer models on a variety of datasets using simple tricks and careful considerations.

VideoGPT: Video Generation using VQ-VAE and Transformers

Repositorio oficial del curso IIC2233 Programación Avanzada 🚀✨

[ECCV'20] Convolutional Occupancy Networks

BOVText: A Large-Scale, Multidimensional Multilingual Dataset for Video Text Spotting

《Single Image Reflection Removal Beyond Linearity》(CVPR 2019)

High dimensional black-box optimizer using Latent Action Monte Carlo Tree Search algorithm

[ICCV 2021] Released code for Causal Attention for Unbiased Visual Recognition