OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Moment

MOMENT is an open family of foundation models for time-series analysis, with pretrained checkpoints and a Python package for forecasting, classification, anomaly detection, imputation and representation learning.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Moment — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use MOMENT when a time-series project needs a shared pretrained model foundation across forecasting, classification, anomaly detection, imputation or representation learning.

Who it is for

  • Developers building time-series forecasting or analysis workflows.
  • Researchers exploring pretrained models across time-series tasks.
  • Practitioners working on classification, anomaly detection or missing-value imputation.

Documented uses

  • Configure a pretrained model for a forecasting horizon.
  • Set up time-series classification with channel and class parameters.
  • Use reconstruction-mode configuration for anomaly detection or imputation.
  • Generate learned representations through the documented embedding task.
Before you choose

Requirements & limits

The repository is public, identifies the project license as MIT, and recommends Python 3.11.

  • The README demonstrates task configuration through MOMENTPipeline and a pretrained Hugging Face checkpoint.
  • Task setup parameters differ: forecasting specifies a horizon, while classification specifies channels and class count.
  • The repository reports different benchmark results across tasks and evaluation settings.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up MOMENT for a forecasting workflow

Install the Python package and initialize a pretrained model configured for forecasting.

Before you start

  • Python 3.11 is the repository's recommended version.
  • The README uses the momentfm package and the AutonLab/MOMENT-1-large pretrained model.

Steps

  1. Install the package with pip install momentfm.

  2. Import MOMENTPipeline from momentfm.

  3. Load AutonLab/MOMENT-1-large with task_name set to forecasting and forecast_horizon set to 96.

  4. Call model.init().

Expected outcome

A pretrained MOMENT pipeline is initialized with forecasting configuration.

Guide limitations

  • The documented example covers model setup and initialization, not preparing input data or producing forecast results.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
moment-timeseries-foundation-model/moment · Official homepage title · retained in its source language
How we review sourcesSuggest a correction