Pinned Repositories
AlignBench
多维度中文对齐评测基准 | Benchmarking Chinese Alignment of LLMs
anything-llm
Open-source ChatGPT equivalent experience for both open and close source LLMs, embedders, and vector databases. Supports unlimited documents, threads, and concurrent users and management all in a very clean UI.
dify
An Open-Source Assistants API and GPTs alternative. Dify.AI is an LLM application development platform. It integrates the concepts of Backend as a Service and LLMOps, covering the core tech stack required for building generative AI-native applications, including a built-in RAG engine.
GPT_API_free
Free ChatGPT API Key，免费ChatGPT API，支持GPT4 API（低价），ChatGPT国内可用免费转发API，直连无需代理。可以搭配ChatBox等软件/插件使用，极大降低接口使用成本。国内即可无限制畅快聊天。
ImageReward
评估人类对文本到图像生成的偏好
llm-action
本项目旨在分享大模型相关技术原理以及实战经验。
MediaCrawler
小红书笔记 | 评论爬虫、抖音视频 | 评论爬虫
MultiCrawler
小红书爬虫，抖音爬虫， 快手爬虫， B站爬虫。视频下载，视频信息爬取。
omniparse
数据清理及结构化工具 OmniParse 该工具能够将各种非结构化数据转化为结构化的、可操作的数据，方便用于检索增强生成（RAG）和微调。无论是文档、表格、图像、视频、音频还是网页，都能将它们清理干净并结构化。
Qwen-Agent
基于 Qwen1.5 构建的代理框架和应用程序，具有函数调用、代码解释器、RAG 和 Chrome 扩展。
kekewind's Repositories
kekewind/tiny-universe
《大模型白盒子构建指南》：一个全手搓的Tiny-Universe
kekewind/app-controller
App-Controller: Allow users to manipulate your App with natural language
kekewind/awesome-generative-ai
A curated list of Generative AI tools, works, models, and references
kekewind/camelot
A Python library to extract tabular data from PDFs 基于PDFMiner，主要用于提取文本和表格，易于使用，底层为C语言实现，不易定制
kekewind/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
kekewind/CogVideo
Text-to-video generation. The repo for ICLR2023 paper "CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers"
kekewind/Controllable-RAG-Agent
This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.
kekewind/CTranslate2
Fast inference engine for Transformer models
kekewind/dataset-viber
Dataset Viber is your chill repo for data collection, annotation and vibe checks.
kekewind/FlareSolverr
Proxy server to bypass Cloudflare protection 绕过 Cloudflare 保护的代理服务器
kekewind/huggingface-inference-toolkit
Hugging Face Inference Toolkit used to serve transformers, sentence-transformers, and diffusers models.Hugging Face Inference Toolkit 是一个HF官方发布的用于在容器中服务 Transformers 模型的工具包。该库提供了默认的预处理、预测和后处理功能，适用于 Transformers、diffusers 和 Sentence Transformers 模型。用户还可以通过自定义 handler.py 文件进行个性化定制。
kekewind/labelU
Data annotation toolbox supports image, audio and video data.
kekewind/llms-from-scratch-cn
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理
kekewind/MegaParse
文件解析器针对 LLM 提取进行了优化，无任何损失 🧠 以适合 LLM 的格式解析 PDF、Docx、PPTx。File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.
kekewind/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。
kekewind/moffee
moffee: Make Markdown Ready to Presentmoffee 是一个开源的幻灯片制作工具，可以将 Markdown 文档转换为干净、专业的幻灯片。moffee 处理布局、分页和样式，让用户可以专注于内容创作。它使用简单的语法来安排和样式化内容，并提供实时的网页界面，用户可以在输入时更新幻灯片，开始幻灯片放映或导出为 PDF
kekewind/nlm-ingestor
This repo provides the server side code for llmsherpa API to connect. It includes parsers for various file formats.
kekewind/omni-engineer
kekewind/open-parse
Improved file parsing for LLM’s
kekewind/penpot
Penpot: The open-source design tool for design and code collaboration
kekewind/PyMuPDF
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
kekewind/RAGMeUp
Generic rag framework to apply the power of LLMs on any given dataset
kekewind/RapidOCR
Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVION and PaddlePaddle. （将PaddleOCR模型做了转换，采用ONNXRuntime推理，速度很快）
kekewind/RECE
[ECCV 2024] Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
kekewind/ReHiFace-S
Real Time High-Fidelity Faceswap
kekewind/SkyScript-100M
SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama
kekewind/UFO
A UI-Focused Agent for Windows OS Interaction.
kekewind/uptrain
UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.
kekewind/WilmerAI
A python application that routes incoming prompts to an LLM by category, and can support a single incoming connection from a front end to many backend connections to LLMs, allowing one AI Assistant to be powered by many models.
kekewind/X-AnyLabeling
Effortless data labeling with AI support from Segment Anything and other awesome models.