tianchiguaixia / ocr_recognitionLinks
微调阿里开源的文字检测模型,利用合合识别返回的OCR结果作为初始训练数据,对模型进行优化训练,使其更加适应1万张图片的具体场景,提高文字识别的精度。
☆9Updated 5 months ago
Alternatives and similar repositories for ocr_recognition
Users that are interested in ocr_recognition are comparing it to the libraries listed below
Sorting:
- 通用版面分析 | 中文文档解析 |Document Layout Analysis | layout paser☆46Updated 11 months ago
- accelerate generating vector by using onnx model☆17Updated last year
- Python implementation of AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, w…☆45Updated 2 months ago
- 大语言模型训练和服务调研☆37Updated last year
- ☆27Updated 7 months ago
- Used for thinking process intervention of reasoning models such as DeepSeek-R1, effectively controlling the reasoning thinking process. 用…☆24Updated last month
- 通用简单工具项目☆18Updated 7 months ago
- the newest version of llama3,source code explained line by line using Chinese☆22Updated last year
- 介绍docker、docker compose的使用。☆20Updated 9 months ago
- This repository provides an implementation of the paper "A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Co…☆69Updated 2 months ago
- 基于Qwen2模型进行通用信息抽取【实体/关系/事件抽取】☆31Updated 10 months ago
- ☆15Updated 11 months ago
- 本项目借助飞桨平台,构建起一套创新的多模型协同系统,实现 PDF 文件到 Markdown 文件的高效、精准转换。☆12Updated 2 months ago
- deepResearch☆38Updated last month
- 百川Dynamic NTK-ALiBi的代码实现:无需微调即可推理更长文本☆47Updated last year
- ☆12Updated 2 months ago
- SearchGPT: Building a quick conversation-based search engine with LLMs.☆45Updated 4 months ago
- TensorRT☆11Updated 4 years 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 last year
- GoGPT中文指令数据集构造☆10Updated last year
- 使用Qwen1.5-0.5B-Chat模型进行通用信息抽取任务的微调,旨在: 验证生成式方法相较于抽取式NER的效果; 为新手提供简易的模型微调流程,尽量减少代码量; 大模型训练的数据格式处理。☆12Updated 8 months ago
- 基于 LoRA 和 P-Tuning v2 的 ChatGLM-6B 高效参数微调☆55Updated 2 years ago
- LLM RAG 应用,支持 API 调用,语音交互。☆11Updated 11 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☆48Updated 8 months ago
- 用于微调LLM的中文指令数据集☆26Updated 2 years ago
- Recursive Abstractive Processing for Tree-Organized Retrieval☆9Updated last year
- Qwen1.5-SFT(阿里, Ali), Qwen_Qwen1.5-2B-Chat/Qwen_Qwen1.5-7B-Chat微调(transformers)/LORA(peft)/推理☆61Updated last year
- ☆19Updated 11 months ago
- ChatGLM2-6B微调, SFT/LoRA, instruction finetune☆108Updated last year
- 大模型预训练中文语料清洗及质量评估 Large model pre-training corpus cleaning☆64Updated 10 months ago