Stars
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Simple high-throughput inference library
Early stopping for PyTorch
Combining tree-boosting with Gaussian process and mixed effects models
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Cubic spline interpolation on multidimensional grids in PyTorch
Patched Attention for Nonlinear Dynamics
Multi-language library for the calculation of spherical harmonics in Cartesian coordinates
Differentiable signal processing on the sphere for PyTorch
Hyprland is an independent, highly customizable, dynamic tiling Wayland compositor that doesn't sacrifice on its looks.
Kernel density estimation on a sphere
Uplift modeling and causal inference with machine learning algorithms
[CIKM'23] Official code for our paper "Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting".
Embed strange attractors using a regularizer for autoencoders
MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.
The geospatial pooling modules for neural networks in PyTorch
Open-source and strong foundation image recognition models.
Dataset of vessel trajectories recorded using AIS in the Ushant region
Pytorch RBF Layer implements a radial basis function layer in Pytorch. Radial Basis networks can be used to approximate functions.
A Python toolbox for performing gradient-free optimization
A clean customizable documentation theme for Sphinx
Implementation of "Delaunay quadrangulation by two-coloring vertices" paper
Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.
Probabilistic reasoning and statistical analysis in TensorFlow
FinRL®: Financial Reinforcement Learning. 🔥