For Med-Gemini, we relabeled the MedQA benchmark; this repo includes the annotations and analysis code.

Companion webpage to the book "Mathematics For Machine Learning"

Evaluating gender and ethnicity bias across 8 LLMs, and using NLE for bias evaluation and mitigation

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

EDS-Pseudo is a hybrid model for detecting personally identifying entities in clinical reports

Get up and running with Llama 3.2, Mistral, Gemma 2, and other large language models.

Predict schizophrenia from brain grey matter (classification).

Machine Learning for Neuroscience Module Spring 2024 (https://www.imperial.ac.uk/study/courses/postgraduate-taught/translational-neuroscience/)

📺 Discover the latest machine learning / AI courses on YouTube.

Code for Quiet-STaR

Python Library for Accessing the Cohere API

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

Large Language Models to Identify Social Determinants of Health in Electronic Health Records | Paper: https://www.nature.com/articles/s41746-023-00970-0

tiktoken is a fast BPE tokeniser for use with OpenAI's models.

Toolkit for building predictive workflows on top of pydata (pandas, scikit-learn, pytorch, keras, etc.).

Repo for the pape Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions

Examples and guides for using the OpenAI API

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

Code to export Mendeley documents and metadata into Notion databases

PMC-Patients

Software platform for clinical neuroimaging studies

HI-ML toolbox for deep learning for medical imaging and Azure integration

Medical Imaging Deep Learning library to train and deploy 3D segmentation models on Azure Machine Learning

A technical report on convolution arithmetic in the context of deep learning

Composable transformations of Python NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB team.

Data and software for building the ACL Anthology.