moved to https://github.com/dmlc/ps-lite

Data and Code for Reproducing "Global Relational Models of Source Code"

Implementation of the paper "Language-agnostic representation learning of source code from structure and context".

Official code repository of "BERTology Meets Biology: Interpreting Attention in Protein Language Models."

[ICLR 2020] Contrastive Representation Distillation (CRD), and benchmark of recent knowledge distillation methods

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Datasets, tools, and benchmarks for representation learning of code.

Code and source for paper ``How to Fine-Tune BERT for Text Classification?``

Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

简洁易用版TinyBert：基于Bert进行知识蒸馏的预训练语言模型

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

CodeXGLUE

Code for the model presented in the paper: "code2seq: Generating Sequences from Structured Representations of Code"

Re-implementation of "CODE2SEQ: GENERATING SEQUENCES FROM STRUCTURED REPRESENTATIONS OF CODE"