Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
Metatrain
Light Logo Dark Logo
Metatrain on GitHub
  • Installation
  • Getting started
    • Quickstart
    • Training YAML Reference
    • Override Architecture’s Default Parameters
    • Restarting and Checkpoints
    • Units
  • Available Architectures
    • Classifier (Experimental)
    • FlashMD (Experimental)
    • GAP
    • LLPR
    • MACE (Experimental)
    • NanoPET (deprecated)
    • PET
    • SOAP-BPNN
  • Tutorials
    • Beginner Tutorials
      • Basic Usage
      • How to prepare data for training
      • Fine-tuning a pre-trained model
      • Training a model from scratch
      • Model validation with parity plots
      • Running molecular dynamics with ASE
    • Advanced Tutorials
      • Transfer Learning (experimental)
      • Computing LLPR uncertainties
      • Training a model with ZBL corrections
      • Fitting generic targets
      • Training or fine-tuning a FlashMD model
      • Multi-GPU training
      • Training with Mixed Stress Structures
      • Training a DOS model
      • Generating and training an LLPR-derived shallow ensemble model
      • Training a Classifier Model
  • Concepts and Design
    • Output naming
    • Fine-tune a pre-trained model
    • Loss functions
    • Auxiliary outputs
    • Training with Batch Bounds
  • Frequently Asked Questions
  • Citing Metatrain
  • Developer documentation
    • Contributing
    • Life Cycle of an Architecture
    • Adding a new architecture
    • Dataset Information
    • Adding a new loss function
    • CLI API
      • Train
      • Eval
      • Export
      • Formatter
    • Utility API
      • Additive models
        • Removing additive contributions
        • Composition model
        • ZBL short-range potential
      • Scaler models
        • Scaler model
        • Removing the scale from targets
      • Data
        • Combining dataloaders
        • Dataset
        • Reading a dataset
        • Readers
        • Target data Writers
        • Converting Systems to ASE
      • Abstract base classes
      • Architectures
      • Augmentation
      • Device
      • Dtype
      • Errors
      • Evaluating a model
      • External Naming
      • Hyperparameters
      • IO
      • Logging
      • Long-range
      • Loss
      • Metrics
      • Neighbor lists
      • Custom omegaconf functions
      • Output gradient
      • Averaging predictions per atom
      • Pydantic utilities
      • Summing over atoms
      • Testing Utilities
      • Data type and device transfers
      • Unit handling
    • Base hyperparameters
    • Changelog
Back to top
View this page
Edit this page

Additive models¶

API for handling additive models in metatrain. These are models that can be added to one or more architectures.

  • Removing additive contributions
  • Composition model
  • ZBL short-range potential
Next
Removing additive contributions
Previous
Utility API
Copyright © 2026, metatrain developers
Made with Sphinx and @pradyunsg's Furo