Stars
Zero-shot Time Series Forecasting with TabPFN (work accepted at NeurIPS 2024 TRL and TSALM workshops)
Open-source platform layer for AI agents in production
TabICLv2: A state-of-the-art tabular foundation model
An open, end-to-end implementation of TabPFN-like foundation models, covering synthetic priors/data, training, and evaluation on TabArena.
Forecastbench Datasets, updated nightly
TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
An extremely fast Python type checker and language server, written in Rust.
Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.
ML models + benchmark for tabular data classification and regression
Autogluon-cloud aims to provide user tools to train, fine-tune and deploy AutoGluon backed models on the cloud. With just a few lines of codes, users could train a model and perform inference on th…
⚡ TabPFN: Foundation Model for Tabular Data ⚡
LC-PLM: long-context protein language model based on BiMamba-S architecture
Context is Key: A Benchmark for Forecasting with Essential Textual Information
Source code and data for the paper "SALT: Sales Autocompletion Linked Business Tables Dataset"
Multi-Agent System Powered by LLMs for End-to-end Multimodal ML Automation
Sharing both practical insights and theoretical knowledge about LLM evaluation that we gathered while managing the Open LLM Leaderboard and designing lighteval!
Redset is a dataset containing three months worth of user query metadata that ran on a selected sample of instances in the Amazon Redshift fleet. We provide query metadata for 200 provisioned and s…
A playbook for systematically maximizing the performance of deep learning models.
Unified Training of Universal Time Series Forecasting Transformers
Chronos: Pretrained Models for Time Series Forecasting
An extremely fast Python package and project manager, written in Rust.
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
Large-scale pretraining and benchmarking for short-term load forecasting.
Friends don't let friends make certain types of data visualization - What are they and why are they bad.
A Software Framework for Neuromorphic Computing