[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Uncertainty Toolbox: a Python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization

PiML (Python Interpretable Machine Learning) toolbox for model development & diagnostics

Training quantile models

Data and code for the paper "Ultra-early prediction of lithium-ion battery performance using mechanism and data-driven fusion model"

cuML - RAPIDS Machine Learning Library

PyTorch implementation for Neural Additive Models

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yo…

[ICML2024] Unified Training of Universal Time Series Forecasting Transformers

The repo for x-ray diffraction pattern crystallography via deep learning.

a simulated xrd pattern database

FITS: Frequency Interpolation Time Series Analysis Baseline

N-BEATS is a neural-network based model for univariate timeseries forecasting. N-BEATS is a ServiceNow Research project that was started at Element AI.

An implementation of Maximum Mean Discrepancy (MMD) as a differentiable loss in PyTorch.

A Library for Advanced Deep Time Series Models.

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

Inference code for Llama models

Mamba SSM architecture

The official code for "One Fits All: Power General Time Series Analysis by Pretrained LM (NeurIPS 2023 Spotlight)"

UUKG: Unified Urban Knowledge Graph Dataset for Knowledge-Enhanced Urban Spatiotemporal Prediction

Official code for article "LLMLight: Large Language Models as Traffic Signal Control Agents".

The imbalanced regression method DenseWeight produces sample weights for data points in regression tasks so that there is a higher emphasis on ML model performance for rare (and often extreme) data…

A Bayesian global optimization package for material design ｜ Adaptive Learning | Active Learning

Bayesian optimization in PyTorch

mRMR (minimum-Redundancy-Maximum-Relevance) for automatic feature selection at scale.

Streamlit — A faster way to build and share data apps.