A post-modern modal text editor.

Configuration with Dataclasses+YAML+Argparse. Fork of Pyrallis

Neighborhood Attention Extension. Bringing attention to a neighborhood near you!

recipe for training fully-featured self supervised image jepa models

High-performance MinHash implementation in Rust with Python bindings for efficient similarity estimation and deduplication of large datasets

Gin provides a lightweight configuration framework for Python

Official repository of the paper "GPR1200: A Benchmark for General-PurposeContent-Based Image Retrieval"

This repo contains the official implementation of ICLR 2024 paper "Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video""

Tantivy is a full-text search engine library inspired by Apache Lucene and written in Rust

Tile primitives for speedy kernels

ASTRA-sim2.0: Modeling Hierarchical Networks and Disaggregated Systems for Large-model Training at Scale

A fast inference library for running LLMs locally on modern consumer-class GPUs

A post-modern modal text editor.

An embedded scheme interpreter in Rust

My notes on everything Linux.

GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm

Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos

LPIPS metric. pip install lpips

Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…

Sticky responsive table of contents component

An efficient pytorch implementation of selective scan in one file, works with both cpu and gpu, with corresponding mathematical derivation. It is probably the code which is the most close to select…

Image compression using CARP

Performance Software for Cyclists, Runners, Triathletes and Coaches

Train vector quantized CLIP models using pytorch lightning

autoencoder

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Distribute and run LLMs with a single file.

[CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"

Open-source Android/Desktop remake of Civ V

Decompose any image into a series of paint strokes using PyTorch