Stars
Minimal pretraining script for language modeling in PyTorch. Supporting torch compilation and DDP. It includes a model implementation and a data preprocessing script.
[ICML 2025] OOD-Chameleon: Is Algorithm Selection for OOD Generalization Learnable?
Efficiently discovering algorithms via LLMs with evolutionary search and reinforcement learning.
A tool for inverting and color correcting scanned film negatives, achieved by simulating the process of analog enlargement..
NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers
A template for starting reproducible Python machine-learning projects with hardware acceleration. Find an example at https://github.com/CLAIRE-Labo/no-representation-no-trust
[NeurIPS 2024] Efficiency for Free: Ideal Data Are Transportable Representations
Saprot: Protein Language Model with Structural Alphabet (AA+3Di)
A collection of AWESOME things about mixture-of-experts
A guided, intuitive introduction to genomics for software engineers. Curated by the community.
[NeurIPS 2023 Spotlight] The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning
A library for efficient similarity search and clustering of dense vectors.
Formalizing and benchmarking open problems in single-cell genomics
Codes for paper: Evaluating the Utilities of Large Language Models in Single-cell Data Analysis.
DANCE: a deep learning library and benchmark platform for single-cell analysis
Reproducing result from the paper
[NeurIPS 2023, KDD MLG 2023] Repo that contains code for the paper titled: "FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations".
✨✨Latest Advances on Multimodal Large Language Models
Long Range Arena for Benchmarking Efficient Transformers
Landmark Attention: Random-Access Infinite Context Length for Transformers
[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333