Starred repositories
【间隙·树·排序算法】 对OCR结果或PDF提取的文本进行版面分析,按人类阅读顺序进行排序。
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。
主要是我是日常看过的不错的文章的资源汇总,方便自己也分享给大家。有些我看过的,就会做简单的解读,没看过的,就先罗列一下,然后之后看了把解读更新上;涉及到搜索/推荐/自然语言处理。
ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型
Making large AI models cheaper, faster and more accessible
Collection of Open Source Projects Related to GPT,GPT相关开源项目合集🚀、精选🔥🔥
Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀
It is a simple library to speed up CLIP inference up to 3x (K80 GPU)
🛠 A lite C++ toolkit of 100+ Awesome AI models, support ORT, MNN, NCNN, TNN and TensorRT. 🎉🎉
Benchmarks of approximate nearest neighbor libraries in Python
Deep Learning Computer Vision Algorithms for Real-World Use
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.
🎥 Python and OpenCV-based scene cut/transition detection program & library.
深度学习入门课、资深课、特色课、学术案例、产业实践案例、深度学习知识百科及面试题库The course, case and knowledge of Deep Learning and AI
bert预训练,分别采用字mask和wwm mask在中文领域内finetune bert模型。
A GPU-accelerated library containing highly optimized building blocks and an execution engine for data processing to accelerate deep learning training and inference applications.
Book_3_《数学要素》 | 鸢尾花书:从加减乘除到机器学习;上架;欢迎继续纠错,纠错多的同学还会有赠书!
The Book of Statistical Proofs
不用tensorflow estimator,分别采用字mask和wwm mask在中文领域内finetune bert模型
一键中文数据增强包 ; NLP数据增强、bert数据增强、EDA:pip install nlpcda
wipen / bert_and_ernie
Forked from google-research/bertTensorFlow code and pre-trained models for BERT and ERNIE
基于mlm方式的带有纠错功能的拼音转汉字bert预训练模型,pinyin correcter,基于pytorch框架实现