d3p10y
Yesssss. You’ve got Stars in your hand. Enter your code here and we’ll add Stars to your account.
UltraBear Education①⑤⑥①①④⓪②⑥⓪⑧
Pinned Repositories
2019Legal-AI-Challenge-Legal-Case-Element-Recognition-solution
Completed this competition in collaboration with Jiang Yan(https://github.com/jy1993) and Guan Shuicheng(https://github.com/guanshuicheng).
A-general-framework-to-Prompt-tuning-LLM-model
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.
A-White-Paper-on-Neural-Network-Deployment
模型部署白皮书(CUDA|ONNX|TensorRT|C++)
AAGPT
AAGPT is another experimental open-source application showcasing the capabilities of large language models, such as GPT-3.5 and GPT-4.
Abdominal-Trauma-Detection-code
AcademiCodec
AcademiCodec: An Open Source Audio Codec Model for Academic Research
acte
A framework to build Tools for AI Agents, a GUI-like solution to enhance Function Calling.
ADI-Stable-Diffusion
Accelerate your Stable Diffusion inference with the library's universal C/C++ framework design, powered by ONNXRuntime & across platforms.
aht20
aht20 full function driver
d3p10y's Repositories
d3p10y/Abdominal-Trauma-Detection-code
d3p10y/AutoDAN-Turbo
d3p10y/AutoRLAIF
AutoRLAIF is a cutting-edge framework designed to revolutionize the fine-tuning of large language models through Reinforcement Learning from AI Feedback (RLAIF).
d3p10y/Bridge3D
d3p10y/Canary_Master
CanarySEFI is a framework for evaluating the robustness of deep learning-based image recognition models. It can evaluate model robustness and attack/defense algorithm effectiveness, encompassing 26 metrics, including 15 models pre-trained by CIFAR-10, CIFAR-100, Fashion-MNIST, and ImageNet (with weights), 20+ attack methods, and 10+ defense methods
d3p10y/CBGBench
Official code repository of CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph
d3p10y/cond-image-leakage
Official implementation for "Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model" (NeurIPS 2024)
d3p10y/CT2CQA
d3p10y/custom-lens-wa-hub
Provide JSON file template that demonstrate how to create customize Well-Architected reviews using Custom lenses.
d3p10y/D-FINE
D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement 💥💥💥
d3p10y/DataFlow-Engine
数据流引擎是一款面向数据集成、数据同步、数据交换、数据共享、任务配置、任务调度的底层数据驱动引擎。数据流引擎采用管执分离、多流层、插件库等体系应对大规模数据任务、数据高频上报、数据高频采集、异构数据兼容的实际数据问题。
d3p10y/engy
Engy is an AI-powered development tool that generates fully functional web applications from natural language, streamlining the process from idea to working prototype.
d3p10y/Everlyn-1
The first open autoregressive foundational video AI model.
d3p10y/GitHub-Stats-SVG
A highly customizable GitHub stats SVG generator: Most readme card projects on GitHub look B-O-R-I-N-G, so I made a cool one myself. Cyberpunk style :)
d3p10y/GpuScript
GpuScript makes your Object-Oriented programs run at supercomputer speeds on a single GPU. Learn it in 30 minutes and you can write & debug large and complex GPU projects.
d3p10y/hallo2
Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation
d3p10y/InnoVault
InnoVault API Mod
d3p10y/KVStore
d3p10y/LeetCode-Solver-Bot
Effortlessly solve LeetCode problems with the power of automation! LeetCode Solver Bot automates fetching problems, generating solutions, debugging, and submission. No more manual coding or debugging—just sit back and let the bot handle the heavy lifting.
d3p10y/LightRAG
"LightRAG: Simple and Fast Retrieval-Augmented Generation"
d3p10y/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。
d3p10y/Magic-BI
One-stop data intelligence agent, providing insights from all mainstream data formats in a single dialogue box, including documents, databases, business systems, and images.一站式数据智能体,一个对话框提供所有主流格式数据的见解,包括文档、数据库、业务系统和图像。
d3p10y/mini-omni2
Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。
d3p10y/qust
d3p10y/rag-men
A Contextual RAG Bot Framework
d3p10y/sdlc_python
sdlc_python 是一个基于python语言构建的devsecops平台,旨在促进 DevSecOps 和安全开发生命周期 (SDLC) 实践。它通过模拟常见漏洞来增强开发人员的安全意识(对应sdlc中对开发人员的安全培训),并且使用了大模型进行代码安全审计(对应sdlc中代码审计阶段),帮助企业进行安全左移。除了用于 DevSecOps 实践外,sdlc_python 还可以用于学习漏洞知识、渗透测试和代码审计。本项目采用了前后端分离的设计模式,其中后端利用了轻量级框架 Flask,而前端则使用了 Vue 3。
d3p10y/SGS-SLAM
[ECCV 2024] SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAM
d3p10y/ThreadPoolUtils
Provide well-tested and validated thread pool utils
d3p10y/virtual_human_stream
The "virtual_human_stream" project is a real-time digital human system supporting audio-video dialogue. It integrates models like ernerf, musetalk, and wav2lip for voice cloning, video stitching, and streaming via RTMP/WebRTC. It’s optimized for high performance and easy customization, with support for ChatGPT dialogue integration.
d3p10y/WorkFlow-Engine
工作流引擎对内提供单位/机关流程管理规则和内部业务流程的数字化落地实践;对外提供自动化地第三方业务驱动、接口接入和算法单元驱动能力。工作流引擎在提供底层驱动引擎的同时对全局透明监控、安全防御和国产化特色功能进行充分考虑,是内部流程管理和业务算法驱动的不二之选。