#
Starred repositories
Code2Prompt is a powerful command-line tool that simplifies the process of providing context to Large Language Models (LLMs) by generating a comprehensive Markdown file containing the content of yo…
SUSHI (aka "SUSHI Unshortens Short Hand Inputs") is a reference implementation command-line interpreter/compiler for FHIR Shorthand (FSH).
Inspect: A framework for large language model evaluations
Graph database optimized for fast analysis and real-time data processing. It is provided as an extension to PostgreSQL.
Tensor parallelism is all you need. Run LLMs on an AI cluster at home using any device. Distribute the workload, divide RAM usage, and increase inference speed.
Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.
Drag & drop UI to build your customized LLM flow
A map of the AI alignment landscape
The development repository for LessWrong2 and the EA Forum, based on Vulcan JS
Poetry lockfile support for Bazel
Bazel rules that use Poetry for Python package management
Forward-Looking Active REtrieval-augmented generation (FLARE)
A guidance language for controlling large language models.
There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable an…
MediaCMS is a modern, fully featured open source video and media CMS, written in Python/Django and React, featuring a REST API.
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Exact structure out of any language model completion.
A library for mechanistic interpretability of GPT-style language models
Prompt tuning toolkit for GPT-2 and GPT-Neo