jannisborn
Follow
Lists (1)
Stars
This is the code accompanying our ICML 2024 paper "Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems".
Implementation of MEGABYTE, Predicting Million-byte Sequences with Multiscale Transformers, in Pytorch
InstructLab Command-Line Interface. Use this to chat with a model and execute the InstructLab workflow to train a model using custom taxonomy data.
An extremely fast Python package and project manager, written in Rust.
Implementation of Alphafold 3 in Pytorch
🏆 A ranked list of awesome python developer tools and libraries. Updated weekly.
Extension of the Monge Gap to learn conditional optimal transport maps
A library for easy and efficient manipulation of tensor networks.
A tiny parser for more flexible conda environment files
Unlock your displays on your Mac! Flexible HiDPI scaling, XDR/HDR extra brightness, virtual screens, DDC control, extra dimming, PIP/streaming, EDID override and lots more!
A reactive notebook for Python — run reproducible experiments, execute as a script, deploy as an app, and version with git.
A programming framework for agentic AI 🤖
Atom-in-SMILES tokenizer for SMILES strings.
Dot access dictionary with dynamic hierarchy creation and ordered iteration
[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333
📋 A list of open LLMs available for commercial use.
Code for "Unifying Molecular and Textual Representations via Multi-task Language Modelling" @ ICML 2023
PyTorch/skopt based implementation of Bayesian optimization with Gaussian processes - build to optimize latent spaces of VAEs to generate molecules with desired properties
DiffLinker: Equivariant 3D-Conditional Diffusion Model for Molecular Linker Design
Supervised Training of Conditional Monge Maps
Making Protein folding accessible to all!
Python package implementing our method MatchCLOT for multimodal single-cell data integration