Learning embeddings for classification, retrieval and ranking.

Python tool for converting files and office documents to Markdown.

This is a text-based game engine that implements the D&D 5th edition ruleset. A sample adventure is included in this repository

The LLM Evaluation Framework

Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali

A Comprehensive Toolkit for High-Quality PDF Content Extraction

Lightweight library for scraping web-sites with LLMs

Data processing with ML, LLM and Vision LLM

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

An open source multi-tool for exploring and publishing data

Pulumi - Infrastructure as Code in any programming language 🚀

Shared data types for building collaborative software

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

HTML to Markdown converter and crawler.

🦙 Integrating LLMs into structured NLP pipelines

Curate better data for LLMs

Automatically Discovering Fast Parallelization Strategies for Distributed Deep Neural Network Training

LLM inference in C/C++

RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, …

A playbook for systematically maximizing the performance of deep learning models.

🧙 Valtio makes proxy-state simple for React and Vanilla

ruptures: change point detection in Python

A list of awesome compiler projects and papers for tensor computation and deep learning.

A universal package of scraper scripts for humans

Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference

Run ONNX and TensorFlow inference in the browser.

Fixes mojibake and other glitches in Unicode text, after the fact.