zrayzzz Goto Github PK

artist

Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking

chinese-llama-alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU部署 (Chinese LLaMA & Alpaca LLMs)

chinesenlpcorpus

搜集、整理、发布 中文 自然语言处理 语料/数据集，与 有志之士 共同 促进 中文 自然语言处理 的 发展。

cluedatasetsearch

搜索所有中文NLP数据集，附常用英文NLP数据集

collie

Collaborative Tuning of Large Language Models in an Efficient Way

cuda_exercise

Cuda exercise from NVIDIA Cuda course

cv-cuda

CV-CUDA™ is an open-source, graphics processing unit (GPU)-accelerated library for cloud-scale image processing and computer vision.

cvat

Powerful and efficient Computer Vision Annotation Tool (CVAT)

d2l-zh

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被60多个国家的400多所大学用于教学。

dialogbot

dialogbot, provide search-based dialogue, task-based dialogue and generative dialogue model. 对话机器人，基于问答型对话、任务型对话、聊天型对话等模型实现，支持网络检索问答，领域知识问答，任务引导问答，闲聊问答，开箱即用。

distribuuuu

The pure and clear PyTorch Distributed Training Framework.

ffmpeg_hw_decode

video stream hardware decoding and color space conversion by ffmpeg and cuda. thread safe.

flagembedding

Dense Retrieval and Retrieval-augmented LLMs

flash-attention-v100

flashattention20triton

Triton implementation of Flash Attention2.0

hungariangpu

An GPU/CUDA implementation of the Hungarian algorithm

llm-pruner

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support LLaMA, Llama-2, BLOOM, Vicuna, Baichuan, etc.

od-weapondetection

Datasets for weapon detection based on image classification and object detection tasks

optimizing-sgemm-on-nvidia-turing-gpus

Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.

particle-filter

A particle filter for tracking multiple humans in high-density crowds

pseco

An official implementation of the PseCo (ECCV2022)

repvgg

RepVGG: Making VGG-style ConvNets Great Again

reviewkd

Distilling Knowledge via Knowledge Review, CVPR 2021

sgn

This is the implementation of CVPR2020 paper “Semantics-Guided Neural Networks for Efficient Skeleton-Based Human Action Recognition”.

tensorrt

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

tensorrtx

Implementation of popular deep learning networks with TensorRT network definition API

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

wanda

A simple and effective LLM pruning approach.

weapons-dataset

wizardlm

Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder and WizardMath