Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

awesome-LLM-resourses

🧑‍🚀 全世界最好的LLM资料总结 | Summary of the world's best LLM resources.
https://github.com/WangRongsheng/awesome-LLM-resourses

Last synced: 6 days ago
JSON representation

评估 Evaluation
- aisuite
- DeepSeek-v3
- lm-evaluation-harness - shot evaluation of language models.
- opencompass - 4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.
- llm-comparator - by-side, developed.
- Ollama Benchmark
- 火山引擎
- 文心千帆
- DashScope
- Groq
- 硅基流动
- VLMEvalKit - source evaluation toolkit of large vision-language models (LVLMs), support ~100 VLMs, 40+ benchmarks.
- EvalScope
- Weave
- Evaluation guidebook
- MixEval
- AGI-Eval
- DeerAPI
- Qwen-Chat
知识库 RAG
- LightRAG - Agent-Generator pipelines.
- RAGLite - Augmented Generation (RAG) with PostgreSQL or SQLite.
- GraphRAG-Ollama-UI
- MiniRAG - augmented generation framework that enables small models to achieve good RAG performance through heterogeneous graph indexing and lightweight topology-enhanced retrieval.
- FlashRAG
- AnythingLLM - in-one AI app for any LLM with full RAG and AI Agent capabilites.
- MaxKB
- RAGFlow - source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
- Dify - 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.
- FastGPT - based platform built on the LLM, offers out-of-the-box data processing and model invocation capabilities, allows for workflow orchestration through Flow visualization.
- Langchain-Chatchat
- QAnything
- Quivr - augmented generation.
- Verba
- GraphRAG - based Retrieval-Augmented Generation (RAG) system.
- TEN - Gen AI-Agent Framework, the world's first truly real-time multimodal AI agent framework.
- nano-GraphRAG - to-hack GraphRAG implementation.
- RAG Techniques - Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.
- ragas
- kotaemon - source clean & customizable RAG UI for chatting with your documents. Built with both end users and developers in mind.
- Fast-GraphRAG
- AutoRAG
- RAGapp
- KAG - guided reasoning and retrieval framework based on OpenSPG engine and LLMs.
- Tiny-GraphRAG
- TurboRAG - Augmented Generation with Precomputed KV Caches for Chunked Text.
- LightRAG - Augmented Generation.
- DB-GPT GraphRAG - GPT GraphRAG integrates both triplet-based knowledge graphs and document structure graphs while leveraging community and document retrieval mechanisms to enhance RAG capabilities, achieving comparable performance while consuming only 50% of the tokens required by Microsoft's GraphRAG. Refer to the DB-GPT [Graph RAG User Manual](http://docs.dbgpt.cn/docs/cookbook/rag/graph_rag_app_develop/) for details.
- Chonkie - nonsense RAG chunking library that's lightweight, lightning-fast, and ready to CHONK your texts.
- RAG-GPT - GPT, leveraging LLM and RAG technology, learns from user-customized knowledge bases to provide contextually relevant answers for a wide range of queries, ensuring rapid and accurate information retrieval.
- CAG
论文 Paper
Tips
书籍 Book
课程 Course
教程 Tutorial
数据 Data
- datasketch
- semhash
- ReaderLM-v2
- Bespoke Curator - Training & Structured Data Extraction.
- AotoLabel
- LabelLLM - Source Data Annotation Platform.
- OmniParser
- MinerU - stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.
- PDF-Extract-Kit - Quality PDF Content Extraction.
- Docling
- GOT-OCR2.0
- Zerox - 4o-mini.
- data-juicer - stop data processing system to make data higher-quality, juicier, and more digestible for LLMs!
- Parsera - sites with LLMs.
- Sparrow - source solution for efficient data extraction and processing from various documents and images.
- pdf-extract-api
- MegaParse
- DocLayout-YOLO - to-Local Adaptive Perception.
- TensorZero
- Promptwright
- LLM Decontaminator
- DataTrove
- llm-swarm
- Tabled
- Distilabel
- Common-Crawl-Pipeline-Creator
- pdf2htmlEX
- Extractous
- MarkItDown
微调 Fine-Tuning
- Online-RLHF
- InternEvo - sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.
- 360-LLaMA-Factory - Tuning of 100+ LLMs. (add Sequence Parallelism for supporting long context training)
- AutoTrain - of-the-art Machine Learning models.
- workbench-llamafactory - to-end model development workflow using Llamafactory.
- TRL
- LLaMA-Factory - Tuning of 100+ LLMs.
- unsloth - 5X faster 80% less memory LLM finetuning.
- Firefly
- Xtuner - featured toolkit for fine-tuning large models.
- torchtune - PyTorch Library for LLM Fine-tuning.
- Ludwig - code framework for building custom LLMs, neural networks, and other AI models.
- aikit - tune, build, and deploy open-source LLMs easily!
- H2O-LLMStudio - a framework and no-code GUI for fine-tuning LLMs.
- LitGPT - of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.
- LLMBox
- PaddleNLP - to-use and powerful NLP and LLM library.
- TinyLLaVA Factory - scale Large Multimodal Models.
- LLM-Foundry
- ChatLearn - scale alignment.
- Meta Lingua - to-hack codebase to research LLMs.
- mistral-finetune - weight codebase that enables memory-efficient and performant finetuning of Mistral's models.
- lmms-finetune - 1.5, qwen-vl, llava-interleave, llava-next-video, phi3-v etc.
- Simplifine
- Transformer Lab - tune, and evaluate large language models on your own computer.
- Liger-Kernel
- Vision-LLM Alignemnt - based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.
- OpenRLHF - to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral).
- nanotron - parallelism training.
- Proxy Tuning
- Effective LLM Alignment
- Autotrain-advanced
智能体 Agents
- LinkAI
- Baidu APPBuilder
- AutoGen - studio.com/)
- AgentGPT
- XAgent
- MobileAgent
- Lagent - based agents.
- Qwen-Agent
- LazyLLM
- AgentScope - empowered multi-agent applications in an easier way.
- MoA - of-the-art results.
- Agently
- Tribe - agent teams.
- CAMEL - agent framework and an open-source community dedicated to finding the scaling law of agents.
- IoA - source framework for collaborative AI agents, enabling diverse, distributed agents to team up and tackle complex tasks through internet-like connectivity.
- Agent Zero
- Agents - source Framework for Data-centric, Self-evolving Autonomous Language Agents.
- FastAgency - agent workflows to production.
- agentUniverse - agent framework that allows developers to easily build multi-agent applications. Furthermore, through the community, they can exchange and share practices of patterns across different domains.
- OmAgent
- Agent-S
- PydanticAI
- CrewAI - playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
- Coze
- Swarm - agent systems. Managed by OpenAI Solutions team. Experimental framework.
- llama-agentic-system
- PraisonAI - code solution for building and managing multi-agent LLM systems, focusing on simplicity, customisation, and efficient human-agent collaboration.
- Agentarium - source framework for creating and managing simulations populated with AI-powered agents.
- smolagents
体验 Usage
课程
- 李宏毅 GenAI课程
教程
- YTB：AI Anytime
- YTB: AI超元域
软件
- 沉浸式翻译
- ![Forkers repo roster for @WangRongsheng/awesome-LLM-resourses - LLM-resourses/network/members)
- ![Stargazers repo roster for @WangRongsheng/awesome-LLM-resourses - LLM-resourses/stargazers)
- POT
- Bob
- OpenAI Translator Bob Plugin
推理 Inference
- ollama
- Open WebUI - friendly WebUI for LLMs (Formerly Ollama WebUI).
- Text Generation WebUI
- Xinference
- LangChain - aware reasoning applications.
- LlamaIndex
- TensorRT-LLM - LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs.
- LlamaChat
- RouteLLM - save LLM costs without compromising quality!
- MInference
- Mem0
- SGLang
- GuideLLM
- LLM-Engines - source models (VLLM, SGLang, Together) and commercial models (OpenAI, Mistral, Claude).
- lobe-chat - source, modern-design LLMs/AI chat framework. Supports Multi AI Providers, Multi-Modals (Vision/TTS) and plugin system.
- vllm - throughput and memory-efficient inference and serving engine for LLMs.
- NVIDIA ChatRTX
- LM Studio
- chat-with-mlx
- LLM Pricing
- Open Interpreter
- Chat-ollama
- chat-ui
- MemGPT - term memory and custom tools.
- koboldcpp - file way to run various GGML and GGUF models with KoboldAI's UI.
- LLMFarm
- enchanted
- Flowise
- Jan - LLM).
- LMDeploy
- AirLLM
- LLMHub
- YuanChat
- LiteLLM
- OARC - TTS speech models, Keras classifiers, Llava vision, Whisper recognition, and more to create a unified chatbot agent for local, custom automation.
- g1 - 3.1 70b on Groq to create o1-like reasoning chains.
- MemoryScope - term memory capabilities, offering a framework for building such abilities.
- OpenLLM - source LLMs, such as Llama 3.1, Gemma, as OpenAI compatible API endpoint in the cloud.
- Infinity - native database built for LLM applications, providing incredibly fast hybrid search of dense embedding, sparse embedding, tensor and full-text.
- optillm - of-the-art techniques that can improve the accuracy and performance of LLMs.
- ZhiLight
- LLaMA Box
- DashInfer - leading performance atop various hardware architectures.
RAG
- LightRAG - Agent-Generator pipelines.
搜索 Search
- OpenSearch GPT
- nanoPerplexityAI - source implementation of perplexity.ai.
- curiosity - like user experience.
- MindSearch - based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT).

Programming Languages

Python 111 Jupyter Notebook 24 TypeScript 14 C++ 5 JavaScript 4 HTML 3 Swift 3 Go 3 Rust 2 C 2

Categories

课程 Course 47 推理 Inference 43 Tips 43 论文 Paper 33 微调 Fine-Tuning 32 教程 Tutorial 32 知识库 RAG 31 数据 Data 29 智能体 Agents 29 评估 Evaluation 19 书籍 Book 17 体验 Usage 8 软件 6 搜索 Search 4 教程 2 课程 1 RAG 1

Sub Categories

Keywords

llm 71 gpt 31 llama 29 ai 28 rag 25 llms 23 openai 21 large-language-models 20 python 20 chatgpt 18 agent 17 llama3 15 chatbot 14 llama2 13 gpt-4 13 pytorch 12 mistral 11 llmops 10 fine-tuning 10 langchain 9 ollama 9 qwen 9 deep-learning 9 machine-learning 9 transformers 8 generative-ai 8 llava 8 llm-inference 7 artificial-intelligence 7 llm-training 7 nlp 7 framework 7 pdf 7 finetuning 6 gemma 6 lora 6 chatglm 6 retrieval-augmented-generation 6 qlora 5 inference 5 language-model 5 llamacpp 5 agents 5 cuda 5 llm-serving 5 transformer 5 genai 5 llm-agent 5 huggingface 5 evaluation 4