Official repository for the study "Evaluating Large Language Model-Generated Brain MRI Protocols: Performance of GPT4o, o3-mini, DeepSeek-R1 and Qwen2.5"

Control Any Computer Using LLMs.

3D Slicer Plugin for Segment anything in medical images

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

A multi-agent AI research system designed to know what it knows (and doesn't know) when conducting research and creating content.

A generative AI extension for JupyterLab

Moxin is a family of fully open-source and reproducible LLMs

See the ROADMAP repository

Get your documents ready for gen AI

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Structured Text Generation

Official inference framework for 1-bit LLMs

AMEGA-LLM: Autonomous Medical Evaluation for Guideline Adherence of Large Language Models

Electronic Health Record Analysis with Python.

Enforce the output format (JSON Schema, Regex etc) of a language model

A modular graph-based Retrieval-Augmented Generation (RAG) system

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

A simple pip-installable Python tool to generate your own HTML citation world map from your Google Scholar ID.

A guidance language for controlling large language models.

Multiple dispatch in Python

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

PARROT is a collaborative initiative to create and annotate radiology reports to facilitate the access to high-quality multi-lingual medical data for the NLP community

Container with utility scripts for medical image analysis

Curated list of datasets and tools for post-training.

LLM training in simple, raw C/CUDA

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Softmax for Arbitrary Label Trees (SALT) is a framework for training segmentation networks using conditional probabilities to model hierarchical relationships in the data.