Fast State-of-the-Art Static Embeddings

SONAR, a new multilingual and multimodal fixed-size sentence embedding space, with a full suite of speech and text encoders and decoders.

Simple, fast primitives for building pdf viewers. maintained by @unriddle-ai

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

A Storybook builder powered by Parcel

Blazingly fast LLM inference.

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Finetune Llama 3.3, DeepSeek-R1 & Reasoning LLMs 2x faster with 70% less memory! 🦥

DSPy: The framework for programming—not prompting—language models

docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning.

Incorporating VIsual LAyout Structures for Scientific Text Classification

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

A React component to view a PDF document

Efficient few-shot learning with Sentence Transformers

OCR, layout analysis, reading order, table recognition in 90+ languages

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

收集并整理有关OCR的数据集并统一标注格式，以便实验需要

Make your JSON data collaborative and version-controlled with CRDTs

A toolchain for web projects, aimed to provide functionalities to maintain them. Biome offers formatter and linter, usable via CLI and LSP.

WIP GitHub client built with React Aria Components + Tailwind CSS

Convert PDF to HTML without losing text or format.

Minimalist ML framework for Rust

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

A Python library to extract tabular data from PDFs

Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.

Rust library for walking directories recursively.

A boilerplate for creating a Llama 3 chat app

A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine

Scalable, Low-latency and Hybrid-enabled Vector Search in Postgres. Revolutionize Vector Search, not Database.