hzauzxb / guidance-ocr
视觉信息抽取任务中，使用OCR识别结果规范多模态大模型的回答
☆25Updated last month
Alternatives and similar repositories for guidance-ocr:
Users that are interested in guidance-ocr are comparing it to the libraries listed below
- 通用版面分析 | 中文文档解析 |Document Layout Analysis | layout paser☆46Updated 8 months ago
- 该项目是为了使用layoutlmv3针对中文图片训练和推理。 其中主要解决三个问题： 1.数据标准化成可以的训练数据集格式 2.layoutlmv3-base-chinese 分词修改 2.超过512长度的文本切分和滑窗操作☆42Updated 5 months ago
- ☆77Updated last month
- ☆165Updated 11 months ago
- ☆56Updated last year
- 【ArXiv】PDF-Wukong: A Large Multimodal Model for Efficient Long PDF Reading with End-to-End Sparse Sampling☆111Updated 4 months ago
- Vary-tiny codebase upon LAVIS （for training from scratch）and a PDF image-text pairs data (about 600k including English/Chinese)☆78Updated 5 months ago
- SearchGPT: Building a quick conversation-based search engine with LLMs.☆44Updated last month
- GOT的vLLM加速实现 并结合 MinerU 实现RAG中的pdf 解析☆46Updated 3 months ago
- ICDAR 2024 Table OCR Model☆28Updated 2 months ago
- ☆25Updated 4 months ago
- ☆12Updated 5 months ago
- chinese document classification of layoutlmv3 and layoutxlm☆42Updated 2 years ago
- Building a VLM model starts from the basic module.☆12Updated 10 months ago
- 如需体验textin文档解析，请点击https://cc.co/16YSIy☆73Updated 3 months ago
- the newest version of llama3，source code explained line by line using Chinese☆22Updated 10 months ago
- ☆32Updated 2 months ago
- 1st Solution For Conversational Multi-Doc QA Workshop & International Challenge @ WSDM'24 - Xiaohongshu.Inc☆163Updated 11 months ago
- Datasets and Evaluation Scripts for CompHRDoc☆33Updated 10 months ago
- official code for "Fox: Focus Anywhere for Fine-grained Multi-page Document Understanding"☆139Updated 8 months ago
- ☆21Updated 6 months ago
- 基于baichuan-7b的开源多模态大语言模型☆73Updated last year
- MPB (Miner-PDF-Benchmark) is an end-to-end PDF document comprehension evaluation suite designed for large-scale model data scenarios.☆21Updated 2 months ago
- Evaluation of the Optical Character Recognition (OCR) capabilities of GPT-4V(ision)☆122Updated last year
- ☆115Updated last year
- ☆53Updated 7 months ago
- Qwen-WisdomVast is a large model trained on 1 million high-quality Chinese multi-turn SFT data, 200,000 English multi-turn SFT data, and …☆18Updated 10 months ago
- [Paper] Code for the EMNLP2023 (Findings) paper "Global Structure Knowledge-Guided Relation Extraction Method for Visually-Rich Document"☆16Updated last year
- The official PyTorch implementation of SEMv3.☆34Updated 8 months ago
- 文档图像处理工具(Document image processing tool)，包括漂白 / 文字方向矫正 / 清晰增强 / 笔记去噪美化 / 去阴影 / 扭曲矫正 / 切边增强(DocBleach / TextOrientationCorrection / DocSha…☆37Updated 5 months ago