yliuhb

fastembed

Fast, Accurate, Lightweight Python library to make State of the Art Embedding

OnnxOCR

基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快

ragflow

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

graphrag

A modular graph-based Retrieval-Augmented Generation (RAG) system

flash-attention

Fast and memory-efficient exact attention

ceph

Ceph is a distributed object, block, and file storage platform

self-llm

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合**宝宝的部署教程

LLaMA-Factory

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

LLM101n

LLM101n: Let's build a Storyteller

translation-agent

llm-action

本项目旨在分享大模型相关技术原理以及实战经验。

ChatTTS

A generative speech model for daily dialogue.

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

Skywork

Skywork series models are pre-trained on 3.2TB of high-quality multilingual (mainly Chinese and English) and code data. We have open-sourced the model, training data, evaluation data, evaluation methods, etc. 天工系列模型在3.2TB高质量多语言和代码数据上进行预训练。我们开源了模型参数，训练数据，评估数据，评估方法。

annotated-transformer

An annotated implementation of the Transformer paper.

bert_score

BERT score for text generation

AISystem

AISystem 主要是指AI系统，包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术

awesome-ai-agents

A list of AI autonomous agents

notable

The Markdown-based note-taking app that doesn't suck.

AppFlowy

Bring projects, wikis, and teams together with AI. AppFlowy is an AI collaborative workspace where you achieve more without losing control of your data. The best open source alternative to Notion.

llm-numbers

Numbers every LLM developer should know

Book3_Elements-of-Mathematics

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！

BELLE

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

dify

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

EmotiVoice

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

CV

✔（已完结）最全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】

pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

text-clustering

Easily embed, cluster and semantically label text datasets

llm-hallucination-survey

Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"

llm_interview_note

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题