Pinned Repositories
ChatMed
ChatMed: 中文医疗大模型，善于在线回答患者/用户的日常医疗相关问题！
Chinese-LlaMA2
Repo for adapting Meta LlaMA2 in Chinese! META最新发布的LlaMA2的汉化版！ （完全开源可商用）
daguan_competition_2021_codes
ECNU-transformers-learning-groups-2022
Medical-ChatGLM
Fine-tuning ChatGLM on medical corpus!
PCEE-BERT
PromptCBLUE
PromptCBLUE: a large-scale instruction-tuning dataset for multi-task and few-shot learning in the medical domain in Chinese
PrompTS
A repo for instruction tuning of time series data. One of the first attempts to apply LLMs into time series studies!
ShenNong-TCM-LLM
Repo for ShenNong-TCM-LLM (“神农”大模型，首个中医药中文大模型)
Text2DT_Baseline
michael-wzhu's Repositories
michael-wzhu/mpnet_zh
A chinese version MPNet (https://arxiv.org/pdf/1905.02450.pdf)
michael-wzhu/BabelNet-Sememe-Prediction
Code and data of the AAAI-20 paper "Towards Building a Multilingual Sememe Knowledge Base: Predicting Sememes for BabelNet Synsets"
michael-wzhu/BERT-Relation-Extraction
PyTorch implementation for "Matching the Blanks: Distributional Similarity for Relation Learning" paper
michael-wzhu/bert4keras
light reimplement of bert for keras
michael-wzhu/BlingFire
A lightning fast Finite State machine and REgular expression manipulation library.
michael-wzhu/bluebert
BlueBERT, pre-trained on PubMed abstracts and clinical notes (MIMIC-III).
michael-wzhu/chaizi
漢語拆字字典
michael-wzhu/corpora
Parallel corpora for the biomedical domain
michael-wzhu/Covid19-NLP
Chinese Medical Dialogue Dataset for COVID19 Consultant
michael-wzhu/Doctor
基于知识图谱的医学诊断系统。Medical Diagnosis System Based on Knowledge Map.
michael-wzhu/DrQA
Reading Wikipedia to Answer Open-Domain Questions
michael-wzhu/gpt-2
Code for the paper "Language Models are Unsupervised Multitask Learners"
michael-wzhu/GPT2-chitchat
GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI**)
michael-wzhu/keras_adversarial_training
Adversarial Training for NLP in Keras
michael-wzhu/MASS
MASS: Masked Sequence to Sequence Pre-training for Language Generation
michael-wzhu/Megatron-LM
Ongoing research training transformer language models at scale, including: BERT & GPT-2
michael-wzhu/milvus
Milvus is an open source vector similarity search engine.
michael-wzhu/nboost
NBoost is a scalable, search-api-boosting platform for deploying transformer models to improve the relevance of search results on different platforms (i.e. Elasticsearch)
michael-wzhu/Neural-Snowball
Code and dataset of AAAI2020 Paper Neural Snowball for Few-Shot Relation Learning
michael-wzhu/OpenHowNet
Core Data of HowNet and OpenHowNet Python API
michael-wzhu/OpenNRE
An Open-Source Package for Neural Relation Extraction (NRE)
michael-wzhu/Python
All Algorithms implemented in Python
michael-wzhu/rezero
Official PyTorch Repo for "ReZero is All You Need: Fast Convergence at Large Depth"
michael-wzhu/RobustDARTS
Understanding and Robustifying DARTS
michael-wzhu/SG-Net
SG-Net: Syntax-guided machine reading comprehension (AAAI 2020)
michael-wzhu/spert
PyTorch code for SpERT: Span-based Entity and Relation Transformer
michael-wzhu/transformers_without_tears
Transformers without Tears: Improving the Normalization of Self-Attention
michael-wzhu/uda
Unsupervised Data Augmentation (UDA)
michael-wzhu/v2rayN
michael-wzhu/Zero-Shot-Cross-Lingual-NER
A repository for our AAAI-2020 Cross-lingual-NER paper. Code will be updated shortly.