katielink

esm

medplum

Medplum is a healthcare platform that helps you quickly develop high-quality compliant applications.

GPT4DFCI

A private and secure generative AI tool, based on GPT-4 and deployed for non-clinical use at Dana-Farber Cancer Institute

chug

Minimal sharded dataset loaders, decoders, and utils for multi-modal document, image, and text datasets.

awell-score

An open source API to perform clinically validated score calculations.

mem0

The memory layer for Personalized AI

cookbook

Open-source AI cookbook

professional-programming

A collection of learning resources for curious software engineers

xmc.dspy

In-Context Learning for eXtreme Multi-Label Classification (XMC) using only a handful of examples.

milvus

A cloud-native vector database, storage for next generation AI applications

RAGatouille

Easily use and train state of the art late-interaction retrieval methods (ColBERT) in any RAG pipeline. Designed for modularity and ease-of-use, backed by research.

WhisperKit

On-device Speech Recognition for Apple Silicon

MedSAM

Segment Anything in Medical Images

SpeziLLM

A module enabling the integration of Large Language Models (LLMs) with the Spezi Ecosystem

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

EhrAgent

[preprint'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records

ToolBench

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

axolotl

Go ahead and axolotl questions

system-design-primer

Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

AppAgent

AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

open-med-calc

OpenMedCalc is a free, open-source medical calculation API

lm-evaluation-harness

A framework for few-shot evaluation of language models.

DuckTrack

Multimodal computer agent data collection program

ProteinGym

Official repository for the ProteinGym benchmarks

rPPG-Toolbox

rPPG-Toolbox: Deep Remote PPG Toolbox (NeurIPS 2023)

UCE

UCE is a zero-shot foundation model for single-cell gene expression data

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

ml-engineering

Machine Learning Engineering Open Book

cyclops

Toolkit for evaluating and monitoring AI models in clinical settings

smol-podcaster

smol-podcaster is your autonomous podcast production intern 🐣