keakon
Follow
Stars
Distributed task queue with full async support
A Comprehensive Toolkit for High-Quality PDF Content Extraction
Community maintained fork of pdfminer - we fathom PDF
Open source Python library for converting PDF to DOCX.
PyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
A curated list of resources for using LLMs to develop more competitive grant applications.
HyperOS enhancement module - Make HyperOS Great Again!
Efficient Triton Kernels for LLM Training
A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。
Convert PDF to markdown + JSON quickly with high accuracy
🚀🚀 「大模型」50分钟完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 50 min!
Enhance Tesseract OCR output for scanned PDFs by applying Large Language Model (LLM) corrections.
Official code for our paper, "LoRA-Pro: Are Low-Rank Adapters Properly Optimized? "
An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models(NeurIPS 2024 Spotlight)
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…
A modular graph-based Retrieval-Augmented Generation (RAG) system
🚀 KIMI AI 长文本大模型逆向API【特长：长文本解读整理】，支持高速流式输出、智能体对话、联网搜索、探索版、K1思考模型、长文档解读、图像解析、多轮对话，零配置部署，多路token支持，自动清理会话痕迹，仅供测试，如需商用请前往官方开放平台。
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
A repository of code samples for Vector search capabilities in Azure AI Search.
Netease Youdao's open-source embedding and reranker models for RAG products.
A fast and powerful RPC framework based on ASGI/WSGI.
Real asynchronous file operations with asyncio support.
AirLLM 70B inference with single 4GB GPU
A fast asyncio MySQL/MariaDB driver with replication protocol support
A fast serialization and validation library, with builtin support for JSON, MessagePack, YAML, and TOML