Tensors and Dynamic neural networks in Python with strong GPU acceleration

Unsupervised text tokenizer for Neural Network-based text generation.

Export utility for unconstrained channel pruned models

A simple and effective LLM pruning approach.

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

4 bits quantization of LLaMA using GPTQ

Instruct-tune LLaMA on consumer hardware

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Make your models invariant to changes in scale.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

TorchSig is an open-source signal processing machine learning toolkit based on the PyTorch data handling pipeline.

Everything we actually know about the Apple Neural Engine (ANE)

GeoTorchAI: A Framework for Training and Using Spatiotemporal Deep Learning Models at Scale

Lightning ⚡️ fast forecasting with statistical and econometric models.

Python library to train neural networks with a strong focus on hydrological applications.

Official code repository for NeurIPS 2022 paper "SatMAE: Pretraining Transformers for Temporal and Multi-Spectral Satellite Imagery"

(NeurIPS 2022) Self-Supervised Visual Representation Learning with Semantic Grouping

A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene Understanding

TempestRemap: Remapping software for climate applications

Using optical flow & machine learning to predict PV yield

A light-weighted extension that brings you the best image browsing experience in VS Code, especially for remote / cloud development.

A collaboration friendly studio for NeRFs

Awesome Open Atmospheric, Ocean, and Climate Science

A benchmark dataset for data-driven weather forecasting

Location Oriented Observed Meteorology

xcube is a Python package for generating and exploiting data cubes powered by xarray, dask, and zarr.

Download and access remote sensing data from any platform

Audio-conditioned video texture generation

Implementation of Video Diffusion Models, Jonathan Ho's new paper extending DDPMs to Video Generation - in Pytorch