中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

AWS tutorial code.

Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard

A serverless architecture for orchestrating ETL jobs in arbitrarily-complex workflows using AWS Step Functions and AWS Lambda.

A coding-free framework built on PyTorch for reproducible deep learning studies. 🏆25 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

Semantics-aware BERT for Language Understanding (AAAI 2020)

ALBERT model Pretraining and Fine Tuning using TF2.0

pytorch implementation for Patient Knowledge Distillation for BERT Model Compression

Pretrain and finetune ELECTRA with fastai and huggingface. (Results of the paper replicated !)

⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).

IndoLEM is a comprehensive Indonesian NLU benchmark, comprising three pillars NLP task: morpho-syntax, semantic, and discourse. Presented in COLING 2020.

Implementation of XLNet that can load pretrained checkpoints

Build, Test and Deploy ETL solutions using AWS Glue and AWS CDK based CI/CD pipelines

Build and deploy a serverless data pipeline on AWS with no effort.

CLUE baseline pytorch CLUE的pytorch版本基线

EGI Cloud Information System Provider

This is the implementation of the paper AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning (https://arxiv.org/abs/2205.12410).

This solution helps you deploy ETL processes and data storage resources to create an Insurance Lake using Amazon S3 buckets for storage, AWS Glue for data transformation, and AWS CDK Pipelines. It is originally based on the AWS blog Deploy data lake ETL jobs using CDK Pipelines, and complements the InsuranceLake Infrastructure project

MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices

Extract, transform, and load data for analytic processing using AWS Glue