Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

搜集、整理、发布 中文 自然语言处理 语料/数据集，与 有志之士 共同 促进 中文 自然语言处理 的 发展。

添加🚀流式 Web 服务到 GraphRAG，兼容 OpenAI SDK，支持可访问的实体链接🔗，支持建议问题，兼容本地嵌入模型，修复诸多问题。Add streaming web server to GraphRAG, compatible with OpenAI SDK, support accessible entity link, support advice question, co…

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

使用LoRA对ChatGLM进行微调。

The Economist 经济学人，持续更新

中文大模型能力评测榜单：目前已囊括164个大模型，覆盖chatgpt、gpt-4o、谷歌gemini、Claude3.5、百度文心一言、千问、百川、讯飞星火、商汤senseChat、minimax等商用模型， 以及deepseek-v3、qwen2.5、llama3.3、phi-4、glm4、书生internLM2.5等开源大模型。不仅提供能力评分排行榜，也提供所有模型的原始输出结果！

LlamaIndex is the leading framework for building LLM-powered agents over your data.

full-scale introduce for elasticsearch

Benchmarks of Deep Neural Networks

Google Research

Benchmarks of approximate nearest neighbor libraries in Python

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

A latent text-to-image diffusion model

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

算法工程师-机器学习面试题总结

An exemplary real-world application built with Vue.js, Vuex, axios and different other technologies. This is a good example to discover Vue for beginners.

Open-source vector similarity search for Postgres

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

A high-throughput and memory-efficient inference and serving engine for LLMs

Notebooks & Example Apps for Search & AI Applications with Elasticsearch

Automatically Generated d2l-zh TensorFlow Notebooks for Colab

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Java version of LangChain

C++ Parallel Computing and Asynchronous Networking Framework

✏️ LeetCode solutions in C++ 11 and Python3

《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

Spring AI+Ollama+pgvector实现本地RAG

Consul is a distributed, highly available, and data center aware solution to connect and configure applications across dynamic, distributed infrastructure.

本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为TensorFlow 2.0实现，项目已得到李沐老师的认可