rane2021 Goto Github PK

2048-dqn

Training a double duel Q-learning agent to achieve the 2048 tile in the Puzzle Game 2048, within 3 hours constraint using google Colab GPU.

2048.c

Console version of the game "2048" for GNU/Linux

anylabeling

Effortless AI-assisted data labeling with AI support from Segment Anything and YOLO!

breakout

Terminal breakout for UNIX

chatglm6b-fastertransformer

use Fastertransformer optimize chatglm-6b v1

chinese-vicuna

Chinese-Vicuna: A Chinese Instruction-following LLaMA-based Model —— 一个中文低资源的llama+lora方案，结构参考alpaca

coco_yolo_label_tool

目标检测简单标注工具，支持coco+yolov5的数据格式

cuda-neural-network

Convolutional Neural Network with CUDA (MNIST 99.23%)

cuda-programming-guide-in-chinese

This is a Chinese translation of the CUDA programming guide

cuda_freshman

deeplearning-based-feature-extraction-and-matching

Integrate SuperPoint and LightGlue into OpenCV image stitching algorithm

fastertransformer-llama

Transformer related optimization, including LLaMA, BERT, GPT

finetune-anything

Fine-tuning SAMs for class-aware computer vision tasks in specific scenarios

ggml-2023-3-29

backup ggml 2023-3-29

hip-examples

Examples for HIP

how_to_optimize_in_gpu

This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.

jogo-breakout-no-terminal

Um jogo simples, feito para jogar em prompts de comando, o game não é otimizado, mas o intuito principal dele era exercitar programação para jogos

label-studio-yolov5-backend

## YoloV5 ML backend for label-studio for semi-automatic labeling

learn_tvm

learn tvm

llama.cpp-ggml

Port of Facebook's LLaMA model in C/C++

matmul_optim

cuda 矩阵优化算法

medicalgpt

MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现包括二次预训练、有监督微调、奖励建模、强化学习训练。

mergemonster

An unsupervised model merging algorithm for Transformers-based language models.

msnhnet

不依赖三方库的深度学习推理框架

ootdiffusion-train

paddle

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）

perclos-enhanced-yolo-drowsiness-detection-system

基于Perclos＆改进YOLOv7的疲劳驾驶DMS检测系统（源码＆教程）

platypus2-chinese

Platypus2 Chinese fintune updating...

promptcblue

PromptCBLUE: a large-scale instruction-tuning dataset for multi-task and zero-shot learning in the medical domain in Chinese

pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more