梁俊宇's repositories
NESCL
The code repository for the paper: Peijie et al., Neighborhood-Enhanced Supervised Contrastive Learning for Collaborative Filtering. IEEE TKDE, 2023.
CSGHub
CSGHub is an opensource large model assets platform just like on-premise huggingface which helps to manage datasets, model files, codes and more. CSGHub是一个开源、可信的大模型资产管理平台，可帮助用户治理LLM和LLM应用生命周期中涉及到的资产（数据集、模型文件、代码等）。CSGHub提供类似私有化的Huggingface功能，以类似OpenStack Glance管理虚拟机镜像、Harbor管理容器镜像以及Sonatype Nexus管理制品的方式，实现对LLM资产的管理。欢迎关注反馈和Star⭐️
Open-ReplaceAnything
Unofficial Implementation of ReplaceAnything: https://aigcdesigngroup.github.io/replace-anything/
Online-RLHF
A recipe for online RLHF.
Multi
大型Android项目基础架构，AndroidX、Jetpack、Koin、模块化、模块代码权限控制、单Activity多fragment
dingo
A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ultra-low latency.
EartAgent
Ein multimodaler, multi-intelligenter Entwicklungsrahmen
ait
Introducing "ait," "aiself," and "aits"—new pronouns for AI systems. This repo provides definitions and examples to promote their use in referring to artificial intelligence. Contributions and multi-language versions are welcome.
A-White-Paper-on-Neural-Network-Deployment
模型部署白皮书(CUDA|ONNX|TensorRT|C++)
p-seamless-scroll
p-seamless-scroll 是一个轻量级且功能强大的 js 插件，用于创建无缝滚动效果。它支持丰富的自定义配置选项，提供了一系列实用的 API 方法以及事件监听功能。
Awesome-Image-Composition
A curated list of papers, code and resources pertaining to image composition/compositing or object insertion, which aims to generate realistic composite image.
openai4j
Java client library for OpenAI API.Full support for all OpenAI API models including Completions, Chat, Edits, Embeddings, Audio, Files, Assistants-v2, Images, Moderations, Batch, and Fine-tuning.
LLM-And-More
LLM-And-More is a professional, plug-and-play, llm trainer and application builder that guides you through the complete LLM workflow from data to evaluation, from training to deployment, from idea to sevice. / LLM-And-More 是一个专业、开箱即用的大模型训练及应用构建一站式解决方案，包含从数据到评估、从训练到部署、从想法到服务的全流程最佳实践。
WavCraft
Official repo for WavCraft, an AI agent for audio creation and editing
Groma
Grounded Multimodal Large Language Model with Localized Visual Tokenization
IntrinsicProteinSim
Visualization, simulation, manipulation of Intrinsic proteins
VXAdmin
A practical front-end template for Vue3+TypeScript+Vite+Pinia+Vueuse, based on the latest/cutting-edge front-end technologies
KD_ECG
code_all
LEADS
Build your race-ready electric car in 10 minutes with powerful electronic stability control and a modern dashboard.
hercules
aot compiler
VAR
[GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!
docker-compose
docker-compose安装常用软件,均使用官网的镜像 同时提供sh脚本给centos一次性安装各种服务
MagicTime
MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
trickPrompt-engine
AI engine for smart contract audit