Code for Large-Scale Study of Temporal Shift in Health Insurance Claims. Christina X Ji, Ahmed M Alaa, David Sontag. CHIL, 2023. https://arxiv.org/abs/2305.05087

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

🦜🔗 Build context-aware reasoning applications

Inference code for Llama models

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

LlamaIndex is a data framework for your LLM applications

Subset selection / data pruning for weak supervision

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

Estimating the probabilities of caution via deep monotonic twin networks

A modular RL library to fine-tune language models to human preferences

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

An R package for evaluating phenotype algorithms.

An open-source NLP research library, built on PyTorch.

Supercharge Your Model Training

Code for co-training large language models (e.g. T0) with smaller ones (e.g. BERT) to boost few-shot performance

Implementation of Enformer, Deepmind's attention network for predicting gene expression, in Pytorch

[ NeurIPS 2022 ] Official Codebase for "ETAB: A Benchmark Suite for Visual Representation Learning in Echocardiography"

The simplest way to serve AI/ML models in production

Training and serving large-scale neural networks with auto parallelization.

Code for doing machine learning with various EHRs

Dataset of 57 mock medical primary care consultations: audio, consultation notes, human utterance-level transcripts.

Named-entity recognition using neural networks. Easy-to-use and state-of-the-art results.

Code to accompany paper published in Nature Digital Medicine

Code for paper "Evaluating Robustness to Dataset Shift via Parametric Robustness Sets"

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Lite Self-Training

Multi-LexSum is an abstractive summarization dataset for US Civil Rights Lawsuits

TorchXRayVision: A library of chest X-ray datasets and models. Classifiers, segmentation, and autoencoders.

OMOP2OBO: A Python Library for mapping OMOP standardized clinical terminologies to Open Biomedical Ontologies