Repository navigation
glue
- Website
- Wikipedia
中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard
Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard
A coding-free framework built on PyTorch for reproducible deep learning studies. PyTorch Ecosystem. 🏆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.
A serverless architecture for orchestrating ETL jobs in arbitrarily-complex workflows using AWS Step Functions and AWS Lambda.
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).
🛸 Run C++ code on web and create blazingly fast websites! A starter template to easily create WebAssembly packages using type-safe C++ bindings with automatic TypeScript declarations.
AWS tutorial code.
ALBERT model Pretraining and Fine Tuning using TF2.0
Datasets collection and preprocessings framework for NLP extreme multitask learning
Implementation of XLNet that can load pretrained checkpoints
A generalized framework for subspace tuning methods in parameter efficient fine-tuning.