Ballmars
I generally work on random stuff related to observability and distributed systems.
PassioflosChennai, India
Pinned Repositories
A-tutorial-compiler-written-in-Java
For Jack language. Most of codes were commented with their usage, which can be useful for beginner to realize the running principle of a compiler for object-oriented programming language.
AChat
AChat
ai
AI-Optimizer
The next generation deep reinforcement learning tookit
AI_for_Atari
Deep Reinforcement Learning Algorithms for solving Atari 2600 Games
AIGenerateCode
Android谷歌上架马甲包垃圾代码混淆
AndroidPdfRender
apiserver-gin
生产级可用golang api服务端(基于gin)
app-monorepo
🔑 The world's first truly open source crypto wallet runs on all platforms: iOS, Android, Windows, macOS, Linux, Chrome, Firefox... and more. Follow up to get updated.
BallApp
⚽🏀🏉
Ballmars's Repositories
Ballmars/AIGenerateCode
Android谷歌上架马甲包垃圾代码混淆
Ballmars/AudioLCM
PyTorch Implementation of AudioLCM (ACM-MM'24): a efficient and high-quality text-to-audio generation with latent consistency model.
Ballmars/bisheng
Bisheng is an open LLM devops platform for next generation AI applications.
Ballmars/book-recommendation-system
Book Recommendation System
Ballmars/claude-prompt-generator
Ballmars/cocos-engine
Cocos simplifies game creation and distribution with Cocos Creator, a free, open-source, cross-platform game engine. Empowering millions of developers to create high-performance, engaging 2D/3D games and instant web entertainment.
Ballmars/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⭐️
Ballmars/DeepBI
LLM based data scientist, AI native data application. AI-driven infinite thinking redefines BI.
Ballmars/DevOpsGPT
Multi agent system for AI-driven software development. Combine LLM with DevOps tools to convert natural language requirements into working software. Supports any development language and extends the existing code.
Ballmars/Digital-Infrastructure
数字底座是一款面向大型政府、企业数字化转型，基于身份认证、组织架构、岗位职务、应用系统、资源角色等功能构建的统一且安全的管理支撑平台。数字底座基于三员管理模式，具备微服务、多租户、容器化和国产化，支持用户利用代码生成器快速构建自己的业务应用，同时可关联诸多成熟且好用的内部生态应用
Ballmars/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.
Ballmars/duix.ai
Ballmars/dynamicPDB
Dynamic PDB datasets
Ballmars/hallo2
Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation
Ballmars/im
Ballmars/im-server
A high-performance IM server.
Ballmars/KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
Ballmars/llbc
一个简洁、高效、跨平台、多语言支持的服务端开发框架，面向Service及Component，底层c++实现。
Ballmars/MateGen
Next-Generation Interactive Intelligent Programming Assistant
Ballmars/mini-omni2
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
Ballmars/nexa-sdk
Nexa SDK is a comprehensive toolkit for supporting ONNX and GGML models. It supports text generation, image generation, vision-language models (VLM), auto-speech-recognition (ASR), and text-to-speech (TTS) capabilities.
Ballmars/OmDet
Real-time and accurate open-vocabulary end-to-end object detection
Ballmars/orillusion
Orillusion is a pure Web3D rendering engine which is fully developed based on the WebGPU standard.
Ballmars/reactuse
Collection of essential React Hooks Utilities.
Ballmars/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）
Ballmars/synthetic-data-generator
SDG is a component focused on the rapid generation of synthetic data for structured tabular data.
Ballmars/TravelGPT
Ballmars/UFO
A UI-Focused Agent for Windows OS Interaction.
Ballmars/websoft9
Websoft9 is web-based PaaS/Linux Panel for running open source
Ballmars/YiVal
🚀 Evaluate and Evolve.🚀 YiVal is an open source GenAI-Ops framework that allows you to manually or automatically tune and evaluate your AIGC prompts, retrieval configs and fine-tune the model params all at once with your preferred choices of test dataset generation, evaluation algorithms and improvement strategies.