changeAI

transformers-code

手把手带你实战 Huggingface Transformers 课程视频同步更新在B站与YouTube

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥

LaCLIP

[NeurIPS 2023] Text data, code and pre-trained models for paper "Improving CLIP Training with Language Rewrites"

CLIP-based-NSFW-Detector

Baichuan-7B

A large-scale 7B pretraining language model developed by BaiChuan-Inc.

chatme_git

chatme app的服务端和后台管理

Langchain-Chatchat

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

muchat-aio

团队版 ChatGPT Web 应用，多用户，免登录。适合公司、组织或小团体内部使用。Team version of ChatGPT web application- multi-user and no log-in required. Suitable for internal use in companies, organizations or small groups.

ColossalAI

Making large AI models cheaper, faster and more accessible

data-centric-AI

A curated, but incomplete, list of data-centric AI resources.

CVprojects

computer vision projects | 计算机视觉相关好玩的AI项目（Python、C++、embedded system）

BingGPT

Desktop application of new Bing's AI-powered chat (Windows, macOS and Linux)

Fengshenbang-LM

Fengshenbang-LM(封神榜大模型)是IDEA研究院认知计算与自然语言研究中心主导的大模型开源体系，成为中文AIGC和认知智能的基础设施。

ChatGPT_JCM

OpenAI管理界面，聚合了OpenAI的所有接口进行界面操作(所有模型、图片、音频、微调、文件)等，支持Markdown格式(公式、图表，表格)等，后期会一点一点的将OpenAI接口进行接入大家支持一下，右上角点个Star。

ChatGptWxMiniProgram

ChatGpt微信小程序前端程序,使用ChatGPT搭建微信聊天机器人

EVA

EVA Series: Visual Representation Fantasies from BAAI

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)

deep-learning-for-image-processing

deep learning for image processing including classification and object-detection etc.

mmdetection

OpenMMLab Detection Toolbox and Benchmark

micronet

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

micronet