The official GitHub page for the survey paper "A Survey of Large Language Models".

compiler learning resources collect.

Offline Quantization Tools for Deploy.

NART = NART is not A RunTime, a deep learning inference framework.

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

On-Device Training Under 256KB Memory [NeurIPS'22]

QONNX: Arbitrary-Precision Quantized Neural Networks in ONNX

Python implementation of algorithms from Russell And Norvig's "Artificial Intelligence - A Modern Approach"

CMSIS-DSP embedded compute library for Cortex-M and Cortex-A

[ECCV 2022] Implementation of the paper "Locality Guidance for Improving Vision Transformers on Tiny Datasets"

Git的奇技淫巧

CAIRI Supervised, Semi- and Self-Supervised Visual Representation Learning Toolbox and Benchmark

PLCT实验室的公开演讲，或者决定公开的组内报告

Roadmap of DL and ML, some courses, study notes and paper summary

OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

Collect some papers about transformer with vision. Awesome Transformer with Computer Vision (CV)

FlagAI (Fast LArge-scale General AI models) is a fast, easy-to-use and extensible toolkit for large-scale model.

An simple and effective segmentation framework

NASLib is a Neural Architecture Search (NAS) library for facilitating NAS research for the community by providing interfaces to several state-of-the-art NAS search spaces and optimizers.

Collect some papers about transformer for detection and segmentation. Awesome Detection Transformer for Computer Vision (CV)

支持远程办公的中国公司

个人博客，欢迎fork

Production First and Production Ready End-to-End Speech Recognition Toolkit

Awesome Crowd Counting

The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，ConvNeXt，etc. ⭐⭐⭐⭐⭐

Code for visualizing the loss landscape of neural nets