NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images that you can use in downstream generative applications.
Repository Index
142,273 visible repositories in the index
433–456 of 1,943 · Most stars
README file generator, powered by AI.
- readme-generator
- readme
- readme-md-generator
- ai
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.
AI 驱动的学术论文配图生成平台。上传论文 → AI 分析内容生成 Prompt → 一键生成高质量科研配图,还有配套的skill可在主流agent中使用
Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models
Practical bilingual AI prompt library for prompt engineering, work, learning, content, marketing, and everyday use.
- ai
- chinese-prompts
- geo
- prompt-engineering
Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.
Convert code repos into an LLM prompt-friendly format. Mostly built by GPT-4.
mean Average Precision - This code evaluates the performance of your neural net for object recognition.
- machine-learning
- pascal-voc
- average-precision
- ground-truth
A general fine-tuning kit geared toward image/video/audio diffusion models.
- diffusers
- diffusion-models
- fine-tuning
- flux-dev
A more memory-efficient rewrite of the HF transformers implementation of Llama for use with quantized weights.
TokenSpeed is a speed-of-light LLM inference engine.
VirtualWife是一个虚拟数字人项目,支持B站直播,支持openai、ollama
⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡
Unleash Next-Level AI! 🚀 💻 Code Generation: DeepSeek r1 + Claude 3.7 Sonnet - Unparalleled Performance! 📝 Content Creation: DeepSeek r1 + Gemini 2.5 Pro - Superior Quality! 🔌 OpenAI-Compatible. 🌊 Streaming & Non-Streaming Support. ✨ Experience the Future of AI – Today! Click to Try Now! ✨
用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库;24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.
InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions
- chatgpt
- visual-language-learning
- multi-modality
- foundation
Reference implementation for DPO (Direct Preference Optimization)
A 13B large language model developed by Baichuan Intelligent Technology
- artificial-intelligence
- chatgpt
- chinese
- gpt-4
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
- proof-assistant
- lean4
- ai-agents
- ai-for-math
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
The goal of this project is to enable users to create cool web demos using the newly released OpenAI GPT-3 API with just a few lines of Python.
The code used to train and run inference with the ColVision models, e.g. ColPali, ColQwen2, and ColSmol.
- colpali
- information-retrieval
- retrieval-augmented-generation
- vision-language-model