Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)

A high-throughput and memory-efficient inference and serving engine for LLMs

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

Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML

The simplest, fastest repository for training/finetuning medium-sized GPTs.

A browser extension that redirects popular sites to alternative privacy friendly frontends

You like pytorch? You like micrograd? You love tinygrad! ❤️

Cal-Heatmap is a javascript module to create calendar heatmap to visualize time series data

INCEpTION provides a semantic annotation platform offering intelligent annotation assistance and knowledge management.

brat rapid annotation tool (brat) - for all your textual annotation needs

Argilla is a collaboration tool for AI engineers and domain experts to build high-quality datasets

CMS framework for Django

The Abstraction and Reasoning Corpus

A toolkit for end-to-end neural ad hoc retrieval

Cantonese Linguistics and NLP

Tools to download and cleanup Common Crawl data

A curated list of resources for Cross-lingual Information Retrieval (CLIR).

Open source annotation tool for machine learning practitioners.

Matplotlib 3.1 cheat sheet.

Code for ACL '19 paper: Towards Improving Neural Named Entity Recognition with Gazetteers

A WDL, CWL and Python API supporting easy-to-use workflow engine. It is scalable, efficient and cross-platform (Linux/macOS).

Design-by-contract in Python3 with informative violation messages and inheritance

The property-based testing library for Python

An IPython notebook plugin for visualizing ASTs.

N-D labeled arrays and datasets in Python

🎯 Accurate sums and dot products for Python.

Sampling profiler for Python programs

Take a modern Python codebase to the next level of performance.

shiv is a command line utility for building fully self contained Python zipapps as outlined in PEP 441, but with all their dependencies included.

Python and tab completion, better together.