Starred repositories
Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model
Empowering RAG with a memory-based data interface for all-purpose applications!
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
🔥 Turn entire websites into LLM-ready markdown or structured data. Scrape, crawl and extract with a single API.
Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.
A collection of benchmarks and datasets for evaluating LLM.
Build your own second brain with supermemory. It's a ChatGPT for your bookmarks. Import tweets or save websites and content using the chrome extension.
Open-source vector similarity search for Postgres
Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!
AI PC starter app for doing AI image creation, image stylizing, and chatbot on a PC powered by an Intel® Arc™ GPU.
An NVIDIA AI Workbench example project for Retrieval Augmented Generation (RAG)
This is Microsoft-Phi-3-NvidiaNIMWorkshop
使用繁體中文資料集做的 Embedding 模型評測
Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
Infinity is a high-throughput, low-latency REST API for serving text-embeddings, reranking models and clip
A high-throughput and memory-efficient inference and serving engine for LLMs
Test your prompts, agents, and RAGs. Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with comma…
DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
Private & local AI personal knowledge management app.
The China Developer Relations Report is an annual research program initiated by the SegmentFault team and continues to be refined through open collaboration. It offers readers a comprehensive overv…
Netease Youdao's open-source embedding and reranker models for RAG products.
Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing …