Some methods for comparing network representations in deep learning and neuroscience.

Inference code for LLaMA models

Repo for NeurIPS 2023 Spotlight paper "A Spectral Theory of Neural Prediction and Alignment." Abdulkadir Canatar∗, Jenelle Feather∗, Albert J. Wakhloo, & SueYeon Chung. (∗equal contribution)

An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.

Evaluate computational models on their alignment to behavioral and neural measurements in the domain of language

Official implementation of Joint Multidimensional Scaling

A neuroscience library for Python, intended to complement the existing nibabel library.

Machine learning metrics for distributed, scalable PyTorch applications.

Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

[PNAS2021] The neural architecture of language: Integrative modeling converges on predictive processing

A toolbox for accurate single-trial estimates in fMRI time-series data

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Pycortex is a python-based toolkit for surface visualization of fMRI data

Code for the paper "Implicit Representations of Meaning in Neural Language Models"

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

Experiments with distilling large language models.