Pinned Repositories
Advanced-QA-and-RAG-Series
This repository contains advanced LLM-based chatbots for Q&A using LLM agents, and Retrieval Augmented Generation (RAG) and with different databases. (VectorDB, GraphDB, SQLite, CSV, XLSX, etc.)
BestYOLO
🌟Change the world, it will become a better place. | 以科研和竞赛为导向的最好的YOLO实践框架!
DAMO-YOLO
DAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA, and distillation enhancement.
ir-rag-sigir24-persona-rag
KDAT
💥一个专为视觉方向目标检测全流程的标注工具集，全称：Kill Object Detection Annotation Tools。
LEDNet-1
PyTorch codes for "LEDNet: Joint Low-light Enhancement and Deblurring in the Dark" (ECCV2022)
MMA
Modeling Missing Annotations for Incremental Learning in Object Detection
Q-YOLO-My
A Pytorch Quantization for YOLO series: High accuracy, Low latency and Easy to use ~
SASC-YOLOX-1
TinySAM
Official PyTorch implementation of "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"
jie311's Repositories
jie311/CHESS
Contextual Harnessing for Efficient SQL Synthesis
jie311/chonkie
🦛 CHONK your texts with Chonkie ✨ - The no-nonsense RAG chunking library
jie311/DAMO-ConvAI
DAMO-ConvAI: The official repository which contains the codebase for Alibaba DAMO Conversational AI.
jie311/DBCopilot
Code and data for the paper "DBCᴏᴘɪʟᴏᴛ: Scaling Natural Language Querying to Massive Databases"
jie311/docetl
A system for agentic LLM-powered data processing and ETL
jie311/EasyRAG
Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案
jie311/functionary
Chat language model that can use tools and interpret the results
jie311/HivisionIDPhotos
⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。
jie311/illufly
✨🦋 illufly 是自我进化的 Agent 框架: 基于自我进化，快速创造价值
jie311/JioNLP
中文 NLP 预处理、解析工具包，准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com
jie311/JudgeIt-LLM-as-a-Judge
Automation Framework using LLM-as-a-judge to Scale Eval of Gen AI solutions (RAG, Multi-turn, Query Rewrite, Text2SQL etc.); that is a good proxy for human judgement.
jie311/LLaMA-Factory
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
jie311/llm_related
记录大模型相关的一些知识和方法
jie311/M-Schema
a semi-structure representation of database schema
jie311/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。
jie311/onnx-tool
A parser, editor and profiler tool for ONNX models.
jie311/onnx_quant_tool
An onnx-based quantitation tool.
jie311/PDFMathTranslate
PDF scientific paper translation and bilingual comparison - 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 翻译
jie311/phidata
Build AI Agents with memory, knowledge, tools and reasoning. Chat with them using a beautiful Agent UI.
jie311/pr-agent
🚀CodiumAI PR-Agent: An AI-Powered 🤖 Tool for Automated Pull Request Analysis, Feedback, Suggestions and More! 💻🔍
jie311/ProposalLLM
标书大模型（Proposal-LLM Chinese version )
jie311/QDA-SQL
🐦 Generating High Quality multiple type multi-turn Text-to-SQL Q&A training sample with LLM 含中文readme
jie311/qwen_agent
qwen agent
jie311/R2R
Containerized, state of the art Retrieval-Augmented Generation (RAG) system with a RESTful API
jie311/RepoAgent
An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.
jie311/RSL-SQL
RSL-SQL: Robust Schema Linking in Text-to-SQL Generation
jie311/sanic-web
一个轻量级、支持全链路且易于二次开发的大模型应用项目 基于 Dify 、Ollama&Vllm、Sanic 和 Text2SQL 📊 等技术构建的一站式大模型应用开发项目，采用 Vue3、TypeScript 和 Vite 5 打造现代UI。它支持通过 ECharts 📈 实现基于大模型的数据图形化问答，具备处理 CSV 文件 📂 表格问答的能力。同时，能方便对接第三方开源 RAG 系统 检索系统 🌐等，以支持广泛的通用知识问答。
jie311/sql-rl-gen
The SQL-RL-GEN is an algorithm based on a Reinforcement Learning approach with a reward function generated by a LLM to guide the agent's training process in solving the specific text2SQL generation task.
jie311/SwanLab
⚡️SwanLab: your ML experiment notebook. 你的AI实验笔记本，日志记录与可视化AI训练全流程。
jie311/synthetic-data-generator
SDG is a specialized framework designed to generate high-quality structured tabular data.