Stars
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
The best repository showing why transformers might not be the answer for time series forecasting and showcasing the best SOTA non transformer models.
Lightning ⚡️ fast forecasting with statistical and econometric models.
Calculates various features from time series data. Python implementation of the R package tsfeatures.
Code for my book on numerical linear algebra.
Examples and guides for using the OpenAI API
A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning …
Merlion: A Machine Learning Framework for Time Series Intelligence
TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's …
A scikit-learn-compatible library for estimating prediction intervals and controlling risks, based on conformal predictions.
A topic-centric list of HQ open datasets.
Secure and fast microVMs for serverless computing.
Javascript and Python libraries for A/B test analysis
Plugin to integrate Learning to Rank (aka machine learning for better relevance) with Elasticsearch
train models in pytorch, Learn to Rank, Collaborative Filter, Heterogeneous Treatment Effect, Uplift Modeling, etc
Google's Engineering Practices documentation
allRank is a framework for training learning-to-rank neural models based on PyTorch.
Tool for producing high quality forecasts for time series data that has multiple seasonality with linear or non-linear growth.
Based on Thompson sampling with the online bootstrap (Dean Eckles, Maurits Kaptein). http://arxiv.org/abs/1410.4009
A Python implementation of LightFM, a hybrid recommendation algorithm.