Stars
AIFoundation 主要是指AI系统遇到大模型,从底层到上层如何系统级地支持大模型训练和推理,全栈的核心技术。
AISystem 主要是指AI系统,包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
HuggingLLM, Hugging Future.
Learning Large Language Model (LLM)(大语言模型学习)
Awesome LLMs on Device: A Comprehensive Survey
本项目旨在分享大模型相关技术原理以及实战经验(大模型工程化、大模型应用落地)
The official implementation of the paper of CVPR2024: Selective Hourglass Mapping for Universal Image Restoration Based on Diffusion Model
Deep Unfolding Network for Image Super-Resolution (CVPR, 2020) (PyTorch)
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.
Train llm (bloom, llama, baichuan2-7b, chatglm3-6b) with deepspeed pipeline mode. Faster than zero/zero++/fsdp.
train llama on a single A100 80G node using 🤗 transformers and 🚀 Deepspeed Pipeline Parallelism
A prototype repo for hybrid training of pipeline parallel and distributed data parallel with comments on core code snippets. Feel free to copy code and launch discussions about the problems you hav…
基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型,进行下游具体任务微调,涉及Freeze、Lora、P-tuning、全参微调等
中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)
Alpaca Chinese Dataset -- 中文指令微调数据集【人工+GPT4o持续更新】
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
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。
数据挖掘、计算机视觉、自然语言处理、推荐系统竞赛知识、代码、思路
华为Mate系列手机自动抢购脚本,支持Mate60、Mate X5、Mate XT 非凡大师、Mate 70、Mate X6 等机型,。欢迎star和打赏
Implementation of PFLD For 68 Facial Landmarks By Pytorch
Implementation of PFLD(Paper: "A Practical Facial Landmark Detector") by pytorch.