Yikai Wang's starred repositories
gpt_academic
为GPT/GLM等LLM大语言模型提供实用化交互接口,特别优化论文阅读/润色/写作体验,模块化设计,支持自定义快捷按钮&函数插件,支持Python和C++等项目剖析&自译解功能,PDF/LaTex论文翻译&总结功能,支持并行问询多种LLM模型,支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。
whisper.cpp
Port of OpenAI's Whisper model in C/C++
pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Segment-Everything-Everywhere-All-At-Once
[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"
Ask-Anything
[CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.
consistencydecoder
Consistency Distilled Diff VAE
ImageReward
[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation
Stable-Diffusion-NCNN
Stable Diffusion in NCNN with c++, supported txt2img and img2img
FouriScale
Official implementation of FouriScale
LeftRefill
LeftRefill: Filling Right Canvas based on Left Reference through Generalized Text-to-Image Diffusion Model (CVPR2024)
Knockoffs-SPR
Official code repo for our paper "Knockoffs-SPR: Clean Sample Selection in Learning with Noisy Labels".