Open Source AI Math Notes

Tevatron - A flexible toolkit for neural retrieval research and development.

This is a Phi-3 book for getting started with Phi-3. Phi-3, a family of open AI models developed by Microsoft. Phi-3 models are the most capable and cost-effective small language models (SLMs) avai…

精心收集的天涯神贴，不带水印，方便阅读

语音方向实验室/公司/资源/实习等，欢迎推荐或自荐

Adobe CC 2019/2020/2021/2022/2023 GenP Universal Patch 3.0

[CVPR2023] Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution

Print-friendly, minimalist CV page

A Zotero add-on to retrive CNKI meta data. 一个简单的Zotero 插件，用于识别中文元数据

PDF references add-on for Zotero.

A Chrome extension for downloading your ChatGPT history to PNG, PDF or a sharable link

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

提取微信聊天记录，将其导出成HTML、Word、Excel文档永久保存，对聊天记录进行分析生成年度聊天报告，用聊天数据训练专属于个人的AI聊天助手

An Open-source Toolkit for LLM Development

【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

Chat with your documents using local AI

A comprehensive, unified and modular event extraction toolkit.

颈椎病腰突康复指南，为程序员群体提供简单可靠的康复指南。

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

大麦、大麦网 演唱会抢票软件，一个基于 tauri + rust + vue 调用接口的抢票软件。

Pre-Trained Chinese XLNet（中文XLNet预训练模型）

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

汉字拼音数据

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

🕹️ A toolkit for document-level event extraction, containing some SOTA model implementations.

RoBERTa中文预训练模型: RoBERTa for Chinese

Tree edit distance using the Zhang Shasha algorithm

第一个支持中英文双语语音-文本多模态对话的开源可商用对话模型。便捷的语音输入将大幅改善以文本为输入的大模型的使用体验，同时避免了基于 ASR 解决方案的繁琐流程以及可能引入的错误。

Fast and memory-efficient exact attention