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。

Docker Image for Ubuntu Desktop which support HW GPU accelerated GUI apps. you can access the Container with ssh or remote desktop, just like Cloud VM.

An easy-to-use framework for modular RAG

主流ocr算法研究实验性的项目，目前实现了CNN BLSTM CTC架构

农业知识图谱(AgriKG)：农业领域的信息检索，命名实体识别，关系抽取，智能问答，辅助决策

RabbitMQ running on docker

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

一个用于提取简体中文字符串中省，市和区并能够进行映射，检验和简单绘图的python模块

中华人民共和国行政区划：省级（省份）、 地级（城市）、 县级（区县）、 乡级（乡镇街道）、 村级（村委会居委会） ，中国省市区镇村二级三级四级五级联动地址数据。

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT,Cross Encoder

基于规则匹配的问答系统中的解析器，the parser of based rule QA system

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

地址识别，纠错，补全

中文地址切分，及地址补全

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

This is an official implementation for the WTW Dataset in "Parsing Table Structures in the Wild " on table detection and table structure recognition.

Example models using DeepSpeed

Repo for "Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture"

Build Text Rerankers with Deep Language Models

LLM (Large Language Model) FineTuning

Minimal example scripts of the Hugging Face Trainer, focused on staying under 150 lines

A simple toy demo of a local voice assistant with whisper and large language model.

Open Language Pre-trained Model Zoo

This repository contains tutorials and examples for Triton Inference Server

《跟我一起深度学习》

Netease Youdao's open-source embedding and reranker models for RAG products.