shan's repositories
Adala
Adala: Autonomous DAta (Labeling) Agent framework Adala：自主数据（标签）代理框架
baguetter
Baguetter is a flexible, efficient, and hackable search engine library implemented in Python. It's designed for quickly benchmarking, implementing, and testing new search methods. Baguetter supports sparse (traditional), dense (semantic), and hybrid retrieval methods.
chatgpt_academic
科研工作专用ChatGPT拓展，特别优化学术Paper润色体验，支持自定义快捷按钮，支持markdown表格显示，Tex公式双显示，代码显示功能完善，新增本地Python工程剖析功能/自我剖析功能
CogVideo
Text-to-video generation. The repo for ICLR2023 paper "CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers"
CTranslate2
Fast inference engine for Transformer models
Deep-Live-Cam
real time face swap and one-click video deepfake with only a single image (uncensored)
EchoMimic
Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning
FlareSolverr
Proxy server to bypass Cloudflare protection 绕过 Cloudflare 保护的代理服务器
frigate
专为家庭助理设计的完整本地 NVR，具有 AI 对象检测功能。使用 OpenCV 和 Tensorflow 在本地为 IP 摄像机执行实时目标检测。 NVR with realtime local object detection for IP cameras
GalTransl
支持GPT-3.5/GPT-4/Newbing/Sakura等大语言模型的Galgame自动化翻译解决方案 Automated translation solution for visual novels supporting GPT-3.5/GPT-4/Newbing/Sakura
gpt-pilot
PoC for a scalable dev tool that writes entire apps from scratch while the developer oversees the implementation
GPT-SoVITS
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
labelU
Data annotation toolbox supports image, audio and video data.
llamacoder
Open source Claude Artifacts – built with Llama 3.1 405B
llm_aided_ocr
Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.
MetaGPT
🌟 The Multi-Agent Meta Programming Framework: Given one line Requirement, return PRD, Design, Tasks, Repo
metube
自托管 YouTube 下载器（youtube-dl / yt-dlp 的 Web UI） https://github.com/alexta69/metube
MinerU
A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。
MiniCPM-V
MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone
Monkey
【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models
NarratoAI
NarratoAI 是一个自动化影视解说工具，基于LLM实现文案撰写、自动化视频剪辑、配音和字幕生成的一站式流程，助力高效内容创作。
PayloadsAllTheThings
A list of useful payloads and bypass for Web Application Security and Pentest/CTF
prompt-poet
Prompt Poet 模板使用 YAML 和 Jinja2 的混合。模板处理分为两个主要阶段： 渲染：首先，Jinja2 处理输入数据。在此阶段，将执行控制流逻辑、验证数据并将其适当地绑定到变量，并适当地评估模板内的函数。 加载：渲染完成后，输出的是一个结构化的 YAML 文件。这个 YAML 结构由重复的块或部分组成，每个部分都封装成一个 Python 数据结构。这些部分具有以下几个属性： 名称：部件的清晰且人类可读的标识符。 内容：构成提示一部分的实际字符串有效负载。 角色（可选）：指定参与者的角色，帮助区分不同的用户或系统组件。 截断优先级（可选）：确定必要时截断的顺序，具有相同优先级的部分将按照出现的顺序被截断。
PyMuPDF
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
pytorch-lightning
在多个 GPU、TPU 上预训练、微调和部署 AI 模型，无需任何代码更改 ;两个核心包软件 # PyTorch Lightning: Train and deploy PyTorch at scale. # Lightning Fabric: Expert control.
SMS
自动在PC端同步短信验证码
taipy
Turns Data and AI algorithms into production-ready web applications in no time.
textual
使用简单的 Python API 构建复杂的用户界面。在终端和 Web 浏览器中运行您的应用程序。
ToolBench
[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.