RunxinXu

GIT

Source code for ACL-IJCNLP 2021 Long paper: Document-level Event Extraction via Heterogeneous Graph-based Interaction Model with a Tracker.

ChildTuning

Source code for our EMNLP'21 paper 《Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning》

Make-Information-Extraction-Great-Again

An (incomplete) overview of information extraction

TSAR

Source code for "A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction" @ NAACL 2022

ContrastivePruning

Source code for our AAAI'22 paper 《From Dense to Sparse: Contrastive Pruning for Better Pre-trained Language Model Compression》

RunxinXu

CLUE-NER

CL homework.

CL-NMT

CL homework.

DGLGraphParallel

Multi-GPUs data parallel training support on DGL with PyTorch backend

Maven-Index-Crawler

Crawl the popular jars and their usage information in https://mvnrepository.com/

Python

All Algorithms implemented in Python

AliceMind

autoSubmit

北京大学疫情出入校自动填报

Awesome-Efficient-PLM

Must-read papers on improving efficiency for pre-trained language models.

Beijing_Daxuexi_Simple

北京 青年大学习 使用Github Actions自动完成

BERT-related-papers

BERT-related papers

DeMa-BWE

NAACL 2019 paper: Density Matching for Bilingual Word Embedding (Zhou et al., 2019)

DreamInvoker

Electron

fairseq

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

homework-postag

KID

code for "A Double-Graph Based Framework for Frame Semantic Parsing"

lm-human-preferences

Code for the paper Fine-Tuning Language Models from Human Preferences

PKU-SIMSO-FREE

自动申请园区往返

pytorch-distributed

A quickstart and benchmark for pytorch distributed training.

RunxinXu.github.io

✨ Build a beautiful and simple website in literally minutes. Demo at https://beautifuljekyll.com

SimCSE

EMNLP'2021: SimCSE: Simple Contrastive Learning of Sentence Embeddings

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

vicuna-generation

XLM

PyTorch original implementation of Cross-lingual Language Model Pretraining.