Code for the blog "Neural audio codecs: how to get audio into LLMs"

Community-maintained Boltz fork with bug fixes, broader compatibility, and CI.

Ongoing research training transformer models at scale

Phylogenetic orthology inference for comparative genomics

Sparsify transformers with cross-layer transcoders

[ACL 2025] Multi-Agent System for Science of Science

Graphinity: Equivariant Graph Neural Network Architecture for Predicting Change in Antibody-Antigen Binding Affinity

[ICLR 2025] Official Implementation of "Towards Fast, Specialized Machine Learning Force Fields: Distilling Foundation Models via Energy Hessians"

Pop-up dictionary browser extension for language learning. Successor to Yomichan.

[Prototype] A lightweight Python DataFrame library for data processing in PyTorch models

LLM training in simple, raw C/CUDA

Rust port of llm.c by @karpathy

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Genalog is an open source, cross-platform python package allowing generation of synthetic document images with custom degradations and text alignment capabilities.

GeoZarr defines geospatial conventions for storing multidimensional georeferenced grids using the Zarr format

Standard ML interpreter, with relational extensions, implemented in Java

A Python Natural Language Processing Toolkit for Medical Text Generation

Write on Obsidian. Publish to Ghost with a single click.

NLP for evidence-based medicine. https://www.robotreviewer.net/.

Locally run an Instruction-Tuned Chat-Style LLM

Inference code for LLaMA models

A framework for few-shot evaluation of autoregressive language models.

Resources for the shared task on conversational question answering SCAI-QReCC 2022

Better SQL in Jupyter. 📊

Tool to bulk follow accounts related Open Science on Mastodon. Runs at https://germanrepro.github.io/Mastodon-OpenScience/ Based on the DIY webapp to bulk follow sociological accounts on Mastodon b…

Predict the structure of immune receptor proteins

A collection of notebooks to provide examples of using Microns-explorer.org datasets

Genepy is an open source utils package covering a range of useful functions for large scale genomics data analysis in python

A flexible framework for nucleosome profiling of cell-free DNA