A collection of tools to work with Google Earth Engine Python API

Indonesian T0 | Instruction-tuning for low-resource and extremely low-resource Austronesian languages

Turn a STAC catalog into a dask-based xarray

Python library for working with any SpatioTemporal Asset Catalog (STAC)

SpatioTemporal Asset Catalog specification - making geospatial assets openly searchable and crawlable

Tools for geodatabase creation and management

Kolmogorov Arnold Networks

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

Semantic segmentation models with pretrained backbones. PyTorch.

Official implementation of "MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation" in MMSegmentation Framework.

RAGs: Simple implementations of Retrieval Augmented Generation (RAG) Systems

Retrying library for Python

Like grep but for natural language questions. Based on Mistral 7B or Mixtral 8x7B.

A deep learning library for video understanding research.

dbt enables data analysts and engineers to transform their data using the same practices that software engineers use to build applications.

build dw with dbt

Tutorial for video classification/ action recognition using 3D CNN/ CNN+RNN on UCF101

Terraform templates for deploying mage-ai to AWS, GCP and Azure

A repository for hacking Generative Fill with Open Source Tools

Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

Latex code for making neural networks diagrams

🔊 Text-Prompted Generative Audio Model

Implementation of the Llama architecture with RLHF + Q-learning

Obsidian plugin to fetch articles and highlights from Omnivore

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

OCR, layout analysis, reading order, line detection in 90+ languages

Panel: The powerful data exploration & web app framework for Python

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.