gongel

将qq消息转发到微信. 基于webQQ，died.

京东商品监控

Scripts logining to network for DataStream Lab. on Win&Linux

导出微信群成员便于查找导师旗下弟子

No description.

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

Export WeChat files to Email automatically because WeChat files on phone will be invalid in several days.

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

PaddleFormers is an easy-to-use library of pre-trained large language model zoo based on PaddlePaddle.

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

JSON for Modern C++

CUDA Templates for Linear Algebra Subroutines

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0.

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

A Data Streaming Library for Efficient Neural Network Training for PaddlePaddle

No description.

Making large AI models cheaper, faster and more accessible

PaddlePaddle Developer Community

FauxPilot - an open-source GitHub Copilot server

GSum: A General Framework for Guided Neural Abstractive Summarization

Code for ACL 2021 main conference paper "Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances".

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

Transformer decoder/decoding performance comparison: FasterTransformer/PyTorch/LightSeq/PaddleNLP

A PaddlePaddle Speech to Any toolkit.

LightSeq: A High Performance Library for Sequence Processing and Generation

No description.

Transformer related optimization, including BERT, GPT

PaddleSlim is an open-source library for deep model compression and architecture search.

Multi-platform high performance deep learning inference engine (『飞桨』多平台高性能深度学习预测引擎）

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

No description.

A collection of useful .gitignore templates

LaTeX thesis template for Fudan University

Deep Learning Examples

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

NLP made easy

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

Data acquisition tool

No description.