weizhenzhao

data-juicer

A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

llm_dpo

dpo finetuning

chatglm_rlhf

chatglm_rlhf_finetuning

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

deep_training

deep learning

chatglm_finetuning

chatglm 6b finetuning and alpaca finetuning

ColossalAI

Making large AI models cheaper, faster and more accessible

semi-EBM

chemprop

Message Passing Neural Networks for Molecule Property Prediction

AC-VAEGAN-PyTorch

Implementation of a Conditional Variational Auto-Encoder GAN in pytorch

EMTboost

Simulation code for Tweedie Gradient Boosting for Extremely Unbalanced Zero-inflated Data

AppleSiliconSelfBuilds

telematicsSDK-demoapp-flutter-

Demo telematics app for Flutter. The application walks you through the telematics SDK integration. The technology is suitable for UBI (Usage-based insurance), shared mobility, transportation, safe driving, tracking, family trackers, drive-coach, and other driving mobile applications

Broca

recommendation

recommendation models

semantic_matching

语义匹配框架

time_extractor

a useful tool for time extraction

MetaHIN

Source code for KDD 2020 paper "Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation"

ERNIE

Official implementations for various pre-training models of ERNIE-family, covering topics of Language Understanding & Generation, Multimodal Understanding & Generation, and beyond.

MegEngine

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

disruptor

High Performance Inter-Thread Messaging Library

3gpp_vad

3gpp协议26073里面的vad的移植

wsdm2020-solution

Solution of team funny in WSDM2020

WSDM-Adhoc-Document-Retrieval

This is our solution for WSDM - DiggSci 2020. We implemented a simple yet robust search pipeline which ranked 2nd in the validation set and 4th in the test set. We won the gold prize at innovation track and bronze prize at dataset track.

models

Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

Deep-attention-matching-network

DeepUtteranceAggregation

Modeling Multi-turn Conversation with Deep Utterance Aggregation (COLING 2018)

WeChatRobot

微信HOOK、微信机器人 wxhook，数据库解密 微信公众号采集 微信公众号爬虫，企业微信HOOK

EmpatheticDialogues

Dialogue model that produces empathetic responses when trained on the EmpatheticDialogues dataset.

flutter_vignettes

A collection of fun Flutter experiments, created by gskinner, in partnership with Google.