zmfy

OpenHands. 🙌 OpenHands: AI-Driven Development

inference. Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

LocalAI. LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

open-webui. User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

mllm. Fast Multimodal LLM on Mobile Devices

omniparse. Ingest, parse, and optimize any data format ➡️ from documents to multimedia ➡️ for enhanced compatibility with GenAI frameworks

GLM-4. GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

grok-1. Grok open release

guidance. A guidance language for controlling large language models.

grobid. A machine learning software for extracting information from scholarly documents

Vary. [ECCV 2024] Official code implementation of Vary: Scaling Up the Vision Vocabulary of Large Vision Language Models.

computervision-recipes. Best Practices, code samples, and documentation for Computer Vision.

autogen. A programming framework for agentic AI

paper-qa. High accuracy RAG for answering questions from scientific documents with citations

onyx. Open Source AI Platform - AI Chat with advanced features that works with every LLM

quivr. Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

Awesome-Graph-LLM. A collection of AWESOME things about Graph-Related LLMs.

NaLLM. Repository for the NaLLM project

DeepKE. [EMNLP 2022] An Open Toolkit for Knowledge Graph Extraction and Construction

llama_index. LlamaIndex is the leading document agent and OCR platform

ChatIE. The online version is temporarily unavailable because we cannot afford the key. You can clone and run it locally. Note: we set defaul openai key. If keys exceed plan and are invalid, please tell us. The response speed depends on openai. ( sometimes, the official is too crowded and slow)

SeqGPT. SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding

mlflow. The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality AI applications while controlling costs and managing access to models and data.

similarities. Similarities: a toolkit for similarity calculation and semantic search. 相似度计算、匹配搜索工具包，支持亿级数据文搜文、文搜图、图搜图，python3开发，开箱即用。

log.c. A simple logging library implemented in C99

linenoise. A small self-contained alternative to readline and libedit

stb. stb single-file public domain libraries for C/C++

text2vec. text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

llama2.c. Inference Llama 2 in one file of pure C

OpenBLAS. OpenBLAS is an optimized BLAS library based on GotoBLAS2 1.13 BSD version.

VisualGLM-6B. Chinese and English multimodal conversational language model | 多模态中英双语对话语言模型

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

ann-benchmarks. Benchmarks of approximate nearest neighbor libraries in Python

annoy. Approximate Nearest Neighbors in C++/Python optimized for memory usage and loading/saving to disk

chatglm.cpp. C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

JittorLLMs. 计图大模型推理库，具有高性能、配置要求低、中文支持好、可移植等特点

WebCPM. Official codes for ACL 2023 paper "WebCPM: Interactive Web Search for Chinese Long-form Question Answering"

milvus-lite. A lightweight version of Milvus

chroma. Search infrastructure for AI

milvus. Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

reflex. 🕸️ Web apps in pure Python 🐍

fann. Approx nearest neighbor search in Rust

nicegui. Create web-based user interfaces with Python. The nice way.

budibase. AI agents, automations and apps that run your operations. Model agnostic.

yao. ✨ Build AI agents and web apps — with a single binary.

ToolJet. ToolJet is the open-source foundation of ToolJet AI - the enterprise app generation platform for building internal tools, dashboard, business applications, workflows and AI agents 🚀

fastllm. fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。

ChatGLM2-6B. ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

llm. [Unmaintained, see README] An ecosystem of Rust libraries for working with large language models

AITemplate. AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

PySimpleGUI. Python GUIs for Humans! Create any GUI simple or complicated in a way that's intuitive. Launched in 2018. NEW for 2026 - the LGPL3 Version 6. Transforms tkinter, Qt, WxPython, and Remi into a simple, intuitive, and fun experience for both hobbyists and expert users.

InferLLM. a lightweight LLM model inference framework

ggml. Tensor library for machine learning

llama.cpp. LLM inference in C/C++

airllm. AirLLM 70B inference with single 4GB GPU

label-studio. Label Studio is a multi-type data labeling and annotation tool with standardized output format

Baichuan-7B. A large-scale 7B pretraining language model developed by BaiChuan-Inc.

audiocraft. Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

fastapi. FastAPI framework, high performance, easy to learn, fast to code, ready for production

project-based-learning. Curated list of project-based tutorials

ToolBench. [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

LLM-Pruner. [NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.

SpQR. Python

SuperAGI. <⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.

FasterTransformer. Transformer related optimization, including BERT, GPT

ChatGLM-6B. ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

mlc-llm. Universal LLM Deployment Engine with ML Compilation

pandas-ai. Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

chatGLM-6B-QLoRA. 使用peft库，对chatGLM-6B/chatGLM2-6B实现4bit的QLoRA高效微调，并做lora model和base model的merge及4bit的量化（quantize）。

CPM-Bee. 百亿参数的中英文双语基座大模型

gorilla. Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

StableStudio. Community interface for generative AI

stable-diffusion-webui. Stable Diffusion web UI

HugNLP. CIKM2023 Best Demo Paper Award. HugNLP is a unified and comprehensive NLP library based on HuggingFace Transformer. Please hugging for NLP now!😊

ChatGLM-Tuning. 基于ChatGLM-6B + LoRA的Fintune方案

DeepSpeedExamples. Example models using DeepSpeed

OpenDelta. A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

ChatGLM-Efficient-Tuning. Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

Langchain-Chatchat. Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

TaskMatrix. Python

GPT2-Chinese. Chinese version of GPT2 training code, using BERT tokenizer.

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

ColossalAI. Making large AI models cheaper, faster and more accessible

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

linux. Linux kernel source tree

rust-course. 什么？你敢放心的把后背交给 AI? 我赌你不敢，那就来学学 AI 时代最酷、最安全、最快的语言吧。本书拥有全面且深入的讲解、生动贴切的示例、德芙般丝滑的内容，这可能是目前最用心的 Rust 中文学习教程 / Book

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

awesome-c. A curated list of awesome C frameworks, libraries, resources and other shiny things. Inspired by all the other awesome-... projects out there.

CS-Notes. :books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计

awesome-java. Collection of awesome Java project on Github(非常棒的 Java 开源项目集合).

bestJavaer. 现在这个 repo 它已转型为 cxuan-ai-labs：一个普通开发者在 AI 时代的个人实验室，用来记录 AI 文章、工具资源、Agent 实验、模型观察、踩坑复盘，以及一些未必成熟但真实有趣的 AI 作品。旧 Java 内容已归档保留，新主线转向 AI。

athena. Java后端知识图谱🔥 帮助Java初学者成长

server. The Triton Inference Server provides an optimized cloud and edge inferencing solution.

java-bible. :banana: 我的技术摘要

pyflink_learn. 基于 PyFlink 的学习文档，通过一个个小实践，便于大家快速入手 PyFlink

HanLP. Natural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Dependency Parsing, Document Classification

Kashgari. Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

doccano. Open source annotation tool for machine learning practitioners.