Márton Kardos

FastTreeSHAP. Fast SHAP value computation for interpreting tree-based models

tidydraws. A tidybayes-inspired data layer for declarative Bayesian visualisation in Python.

PRISM. Java

GeometricKernels. Geometric kernels on manifolds, meshes and graphs

nss. Example code for particle methods and nss

gphmc. Python

Impulso. Bayesian VAR and SVAR models in Python.

parallel-mcmc. Parallelizing MCMC across the sequence length via Newton's method.

mcx. Express & compile probabilistic programs for performant inference on CPU & GPU. Powered by JAX.

learned_optimization. Python

blayers. The missing layers package for Bayesian regression

nutpie. Python wrapper for nuts-rs

cognax. Build, fit, and sample from cognitive models with JAX + NumPyro.

bayex. Minimal Implementation of Bayesian Optimization in JAX

distrax. Python

joss. The Journal of Open Source Software

h-emcee. Affine invariant Hamiltonian (gradient-based) samplers in JAX

lightweight_mmm. LightweightMMM 🦇 is a lightweight Bayesian Marketing Mix Modeling (MMM) library that allows users to easily train MMMs and obtain channel attribution information.

emcee-jax. An experiment: emcee implemented in JAX

catsu. 🔌 Want one client library for all your embeddings? 💙 Choose Catsu! 🐱

Multiscale-Parametric-t-SNE. ESANN20 paper code repository. This package is a perplexity-free extension of Parametric t-SNE dimensionality reduction method implemented in `Keras` and compatible with `Scikit-learn`.

anvay. anvay is a Flask-based Bengali text processing and topic modeling tool that uses Latent Dirichlet Allocation (LDA) to extract topics from uploaded text files.

CGTM. The code and data of CGTM

SciStanPy. Python wrapper around the Stan programming language, designed particularly for use in natural science applications.

unxt. Unitful Quantities in JAX

dayplot. Calendar heatmaps made super simple and highly customizable

kneed. Knee point detection in Python :chart_with_upwards_trend:

dire-rapids. DiRe accelerated by PyTorch, PyKeOps and cuVS

bamojax. Bayesian Modelling using Jax

dire-jax. DImensionality REduction in JAX

docling. Get your documents ready for gen AI

european_values. Measuring European values of LLMs.

ssm. Bayesian learning and inference for state space models

token-explorer. A simple tool that let's you explore different possible paths that an LLM might sample.

hle. Humanity's Last Exam

cultural-llm-papers. A curated list of research papers and resources on Cultural LLM.

nodevectors. Fastest network node embeddings in the west

dash-mantine-components. Plotly Dash components based on Mantine React Components

bog-nu-analysis. Bayesian regression analysis of Bog.nu ratings.

semhash. Fast Multimodal Semantic Deduplication & Filtering

chinese_keybert. A minimal chinese keywords extraction with BERT

jaxoplanet. Astronomical time series analysis with JAX

snica. Code for the paper 'Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA' @ Neurips'21

libnmf. Optimization and Regularization variants of Non-negative Matrix Factorization (NMF)

flowjax. Python

kent_distribution. Python

srai. Spatial Representations for Artificial Intelligence - a Python library toolkit for geospatial machine learning focused on creating embeddings for downstream tasks

mteb. MTEB: State-of-the-art evaluation of embeddings across languages and modalities

doubleml-for-py. DoubleML - Double Machine Learning in Python

pymc-bart. Python

jax_cosmo. A differentiable cosmology library in JAX

pyhgf. PyHGF: A neural network library for predictive coding

flowMC. Normalizing-flow enhanced sampling package for probabilistic inference in Jax

jax-tqdm. Add a tqdm progress bar to your JAX scans and loops.

mici. Manifold Markov chain Monte Carlo methods in Python

NeuroBayes. Fully and Partially Bayesian Neural Nets

emcee. The Python ensemble sampling toolkit for affine-invariant MCMC

bofire. Experimental design and (multi-objective) bayesian optimization.

jaxley. Differentiable neuron simulations with biophysical detail on CPU, GPU, or TPU.

harmonic. Machine learning assisted marginal likelihood (Bayesian evidence) estimation for Bayesian model selection

nndescent. C++/Python implementation of Nearest Neighbor Descent for efficient approximate nearest neighbor search

model2vec. Fast State-of-the-Art Static Embeddings

diffrax. Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/

thejoker. A custom Monte Carlo sampler for the (gravitational) two-body problem

neural-tangents. Fast and Easy Infinite Neural Networks in Python

merge-tokenizers. Package to align tokens from different tokenizations.

spacy-alignments. 💫 A spaCy package for Yohei Tamura's Rust tokenizations library

ott. Optimal transport tools implemented with the JAX framework, to solve large scale matching problems of any flavor.

geomstats. Computations and statistics on manifolds with geometric structures.

patchworklib. Patchwork for matplotlib: A subplot manager for intuitive layouts in matplotlib and seaborn.

sentence-transformers. State-of-the-Art Embeddings, Retrieval, and Reranking

FASTopic. A Fast, Adaptive, Stable, and Transferable Topic Model (NeurIPS 2024)

jaxns. Probabilistic Programming and Nested sampling in JAX

spopt. Spatial Optimization

llm2vec. Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

emlearn. Machine Learning inference engine for Microcontrollers and Embedded devices

narwhals. Lightweight and extensible compatibility layer between dataframe libraries!

preliz. Exploring and eliciting probability distributions

instructor. structured outputs for llms

KeyphraseVectorizers. Set of vectorizers that extract keyphrases with part-of-speech patterns from a collection of text documents and convert them into a document-keyphrase matrix.

pykan. Kolmogorov Arnold Networks

CausalPy. A Python package for causal inference in quasi-experimental settings

numpyro. Probabilistic programming with NumPy powered by JAX for autograd and JIT compilation to GPU/TPU/CPU.

skada. Domain adaptation toolbox compatible with scikit-learn and pytorch

DaCy. DaCy: The State of the Art Danish NLP pipeline using SpaCy

mistral.rs. Fast, flexible LLM inference

hyperbase. A foundational library for Semantic Hypergraphs

pulearn. Positive-unlabeled learning with Python.

dm_pix. PIX is an image processing library in JAX, for JAX.

datamapplot. Creating beautiful plots of data maps

texpresso. TeXpresso: live rendering and error reporting for LaTeX

EmoArc. Jupyter Notebook

zfit. Model manipulation and fitting library based on TensorFlow and optimised for simple and direct manipulation of probability density functions. Its main focus is on scalability, parallelisation and user friendly experience.

benchy. Fun datasets for some light benchmarks.

scikit-churn. Exploring some issues related to churn

independent_component_analysis. Project done as part of the course on Probabilistic Graphical Models by Pierre Latouche and Pierre-Alexandre Mattei. JAX Implementation of the FastICA algorithm, a Newton's descent algorithm for linear ICA, and a Flax implementation of VAE for non-linear ICA.

dynamax. A Python package for probabilistic state space modeling with JAX

catalogue. Super lightweight function registries for your library

dynamic-nmf. Dynamic Topic Modeling via Non-negative Matrix Factorization

river. 🌊 Online machine learning in Python

ecosystem-watcher. Just keeping an eye on the ecosystem.

bert-sklearn. a sklearn wrapper for Google's BERT model

GPJax. Gaussian processes in JAX and Equinox.

gpax. Gaussian Processes for Experimental Sciences

small-text. Active Learning for Text Classification in Python

synjax. Python

bayeux. State of the art inference for your bayesian models.

rethinking-lda. Code for "Rethinking LDA: Why Priors Matter" (Wallach et. al, 2010).

ken_embeddings. KEN: Relational Data Embeddings

glovpy. Package for interfacing Stanford's C GloVe implementation from Python.

bayesflow. A Python library for efficient Bayesian modeling with deep learning

equinox. Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/

modAL. A modular active learning framework for Python

glom. ☄️ Python's nested data operator (and CLI), for all your declarative restructuring needs. Got data? Glom it! ☄️

blackjax. BlackJAX is a Bayesian Inference library designed for ease of use, speed and modularity.

sklearn-expertsys. Highly interpretable classifiers for scikit learn, producing easily understood decision rules instead of black box models

marvin. an ambient intelligence library

skrub. Machine learning with dataframes

ctransformers. Python bindings for the Transformer models implemented in C/C++ using GGML library.

tokenizations. Robust and Fast tokenizations alignment library for Rust and Python https://tamuhey.github.io/tokenizations/

weasel. 🦦 weasel: A small and easy workflow system

curated-transformers. 🤖 A PyTorch library of curated Transformer models and their composable components

optax. Optax is a gradient processing and optimization library for JAX.

jax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

confection. :candy: Confection: the sweetest config system for Python

GPBoost. Tree-Boosting, Gaussian Processes, and Mixed-Effects Models

causaltune. AutoML for causal inference.

embetter. just a bunch of useful embeddings for scikit-learn pipelines

scandinavian-embedding-benchmark. A Scandinavian Benchmark for sentence embeddings

plotly.py. The interactive graphing library for Python :sparkles:

HSSM. Development of HSSM package

bambi. BAyesian Model-Building Interface (Bambi) in Python.

awkward. Manipulate JSON-like data with NumPy-like idioms.

spaCy. 💫 Industrial-strength Natural Language Processing (NLP) in Python

hnswlib-rs. Rust implementation of the HNSW algorithm (Malkov-Yashunin)

black. The uncompromising Python code formatter

pynndescent. A Python nearest neighbor descent for approximate nearest neighbors

BERTopic. Leveraging BERT and c-TF-IDF to create easily interpretable topics.

umap. Uniform Manifold Approximation and Projection

site. The website for Danish Foundation Models, a project for training foundational Danish language model.