Kevin Canwen Xu's repositories
BERT-of-Theseus
⛵️The official PyTorch implementation for "BERT-of-Theseus: Compressing BERT by Progressive Module Replacing" (EMNLP 2020).
MetaDistil
Code for ACL 2022 paper "BERT Learns to Teach: Knowledge Distillation with Meta Learning".
dogwhistle
Baseline code for NAACL 2021 paper "Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge"
beyond-preserved-accuracy
Repo for EMNLP 2021 paper "Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression"
dope-score-chinese
Automatic metric for evaluating rap lyrics in Chinese (Mandarin).
alpaca_eval
A validated automatic evaluator for instruction-following language models. High-quality, cheap, and fast.
pytorch-apex-docker
Up-to-date Dockerfile for PyTorch + apex
acl-anthology
Data and software for building the ACL Anthology.
alpa
Auto parallelization for large-scale neural networks
chatgpt-google-extension
A browser extension that enhance search engines with ChatGPT
ChineseGLUE
Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard
FastChat
The release repo for "Vicuna: An Open Chatbot Impressing GPT-4"
mosesdecoder
Moses, the machine translation system
promptsource
Toolkit for collecting and applying templates of prompting instances
Sequence_Span_Rewriting
Code for EMNLP 2021 paper: Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting
transformers
🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.