zirui Goto Github PK

challenges

challenges problems

docai

information extraction from doc images

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

hack

some hack stuff

llm-tuning

LLM tuning

longgpt

explore LLM for long text input

ml

mojo

The Mojo Programming Language

ms-amp

Microsoft Automatic Mixed Precision Library

nanotron

Minimalistic large language model 3D-parallelism training

open-assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

paddlenlp

👑 Easy-to-use and powerful NLP library with 🤗 Awesome model zoo, supporting wide-range of NLP tasks from research to industrial applications, including 🗂Text Classification, 🔍 Neural Search, ❓ Question Answering, ℹ️ Information Extraction, 📄 Document Intelligence, 💌 Sentiment Analysis and 🖼 Diffusion AIGC system etc.

paddleocr

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)

poetry

a collection of beautiful poetry

transformerengine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

zirui.github.io

for static blog