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。
☆10Updated last year
Alternatives and similar repositories for ocr_recognition
Users that are interested in ocr_recognition are comparing it to the libraries listed below
Sorting:
- 介绍docker、docker compose的使用。☆21Updated last year
- 大语言模型训练和服务调研☆36Updated 2 years ago
- 通用版面分析 | 中文文档解析 |Document Layout Analysis | layout paser☆48Updated last year
- ☆13Updated 9 months ago
- This repository provides an implementation of "A Simple yet Effective Training-free Prompt-free Approach to Chinese Spelling Correction B…☆85Updated 5 months ago
- Python implementation of AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, w…☆48Updated 9 months ago
- SearchGPT: Building a quick conversation-based search engine with LLMs.☆47Updated 11 months ago
- 通用简单工具项目☆22Updated last year
- ☆15Updated last year
- 基于Qwen2模型进行通用信息抽取【实体/关系/事件抽取】☆40Updated last year
- ☆19Updated last year
- the newest version of llama3，source code explained line by line using Chinese☆22Updated last year
- 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
- accelerate generating vector by using onnx model☆18Updated last year
- 集成Qwen与DeepSeek等先进大语言模型，支持纯LLM+分类层模式及LLM+LoRA+分类层模式，使用transformers模块化设计和训练便于根据需要调整或替换组件。☆17Updated 3 months ago
- 基于python的BM25文本匹配算法实现☆33Updated 3 years ago
- ☆27Updated last year
- 中文原生检索增强生成测评基准☆123Updated 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。☆15Updated last year
- Code & Data for our Paper "NaSGEC: Multi-Domain Chinese Grammatical Error Correction for Native Speaker Texts" (ACL 2023 Findings)☆96Updated 10 months ago
- 百川Dynamic NTK-ALiBi的代码实现：无需微调即可推理更长文本☆49Updated 2 years ago
- （1）弹性区间标准化的旋转位置词嵌入编码器+peft LORA量化训练，提高万级tokens性能支持。（2）证据理论解释学习，提升模型的复杂逻辑推理能力（3）兼容alpaca数据格式。☆45Updated 2 years 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☆62Updated 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☆69Updated 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☆73Updated last year
- 大模型检索增强生成技术最佳实践。☆88Updated last year
- 文本去重☆77Updated last year
- A repo for update and debug Mixtral-7x8B、MOE、ChatGLM3、LLaMa2、 BaChuan、Qwen an other LLM models include new models mixtral, mixtral 8x7b, …☆47Updated 2 months ago
- 基于 LoRA 和 P-Tuning v2 的 ChatGLM-6B 高效参数微调☆55Updated 2 years ago
- llms related stuff , including code, docs☆13Updated 10 months ago