瓜瓜's repositories
AudioLCM
PyTorch Implementation of AudioLCM (ACM-MM'24): a efficient and high-quality text-to-audio generation with latent consistency model.
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.
bisheng
Bisheng is an open LLM devops platform for next generation AI applications.
carefree-drawboard
🎨 Infinite Drawboard in Python
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⭐️
Deep-RL-Notes
A collection of comprehensive notes on Deep Reinforcement Learning, customized for UC Berkeley's CS 285 (prev. CS 294-112)
DeepBI
LLM based data scientist, AI native data application. AI-driven infinite thinking redefines BI.
DevOpsGPT
Multi agent system for AI-driven software development. Convert natural language requirements into working software. Supports any development language and extends the existing base code.
FedML
FedML - The federated learning and analytics library enabling secure and collaborative machine learning on decentralized data anywhere at any scale. Supporting large-scale cross-silo federated learning, cross-device federated learning on smartphones/IoTs, and research simulation. MLOps and App Marketplace are also enabled (https://open.fedml.ai).
hallo
Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
light-gpt
Light-GPT is an interactive website project based on the GPT-3.5-Turbo Model.
Macaw-LLM
Macaw-LLM: Multi-Modal Language Modeling with Image, Video, Audio, and Text Integration
OmDet
Real-time and accurate open-vocabulary end-to-end object detection
Open-Assistant
YORG Open Source Version
Open-ReplaceAnything
Unofficial Implementation of ReplaceAnything: https://aigcdesigngroup.github.io/replace-anything/
orillusion
Orillusion is a pure Web3D rendering engine which is fully developed based on the WebGPU standard.
Otter
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following ability and in-context learning.
reactuse
Collection of essential React Hooks Utilities.
SQLAgent
SQLAgent 是一个 开源的（Open source）、大模型驱动的（LLM-Powered）、专注于私有化部署的Text2SQL 智能体（Agent） 项目（Project）
synthetic-data-generator
SDG is a component focused on the rapid generation of synthetic data for structured tabular data.
TimeMixer
[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"
UFO
A UI-Focused Agent for Windows OS Interaction.
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!
VLM_survey
Vision-Language Models for Vision Tasks: A Survey
websoft9
Websoft9 is web-based PaaS/Linux Panel for running open source
xxim-server
惺惺 —— 属于你的社交地盘！惺惺是一个100%开源社交平台，每个人都可以搭建自己的服务器，掌握数据的所有权。此APP非盈利项目！
YiVal
YiVal is an open source GenAI-Ops framework that allows you to iteratively tune your AIGC model metadata, params, prompts and retrieval configs all at once with your preferred choices of test dataset generation, evaluation algorithms and improvement strategies.