mattertune.configs.backbones.uma.model

class mattertune.configs.backbones.uma.model.FAIRChemAtomsToGraphSystemConfig(*, radius, max_num_neighbors=None)[source]

Configuration for converting ASE Atoms to a graph for the FAIRChem model.

Parameters:

  • radius (float)

  • max_num_neighbors (int | None)

radius: float

The radius for edge construction.

max_num_neighbors: int | None

The maximum number of neighbours each node can send messages to.

class mattertune.configs.backbones.uma.model.FinetuneModuleBaseConfig(*, reset_backbone=False, freeze_backbone=False, reset_output_heads=True, use_pretrained_normalizers=False, properties, optimizer, lr_scheduler=None, ignore_gpu_batch_transform_error=True, normalizers={})[source]
Parameters:

  • reset_backbone (bool)

  • freeze_backbone (bool)

  • reset_output_heads (bool)

  • use_pretrained_normalizers (bool)

  • properties (Sequence[PropertyConfig])

  • optimizer (OptimizerConfig)

  • lr_scheduler (LRSchedulerConfig | None)

  • ignore_gpu_batch_transform_error (bool)

  • normalizers (Mapping[str, Sequence[NormalizerConfig]])

reset_backbone: bool

Whether to reset the backbone of the model when creating the model.

freeze_backbone: bool

Whether to freeze the backbone during training.

reset_output_heads: bool

Whether to reset the output heads of the model when creating the model.

use_pretrained_normalizers: bool

Whether to use the pretrained normalizers.

properties: Sequence[PropertyConfig]

Properties to predict.

optimizer: OptimizerConfig

Optimizer.

lr_scheduler: LRSchedulerConfig | None

Learning Rate Scheduler

ignore_gpu_batch_transform_error: bool

Whether to ignore data processing errors during training.

normalizers: Mapping[str, Sequence[NormalizerConfig]]

Normalizers for the properties.

Any property can be associated with multiple normalizers. This is useful for cases where we want to normalize the same property in different ways. For example, we may want to normalize the energy by subtracting the atomic reference energies, as well as by mean and standard deviation normalization.

The normalizers are applied in the order they are defined in the list.

abstract classmethod ensure_dependencies()[source]

Ensure that all dependencies are installed.

This method should raise an exception if any dependencies are missing, with a message indicating which dependencies are missing and how to install them.

abstract create_model()[source]

Creates an instance of the finetune module for this configuration.

Return type:

FinetuneModuleBase

class mattertune.configs.backbones.uma.model.UMABackboneConfig(*, reset_backbone=False, freeze_backbone=False, reset_output_heads=True, use_pretrained_normalizers=False, properties, optimizer, lr_scheduler=None, ignore_gpu_batch_transform_error=True, normalizers={}, name='uma', model_name, atoms_to_graph=FAIRChemAtomsToGraphSystemConfig(radius=6.0, max_num_neighbors=None), task_name=None)[source]
Parameters:

  • reset_backbone (bool)

  • freeze_backbone (bool)

  • reset_output_heads (bool)

  • use_pretrained_normalizers (bool)

  • properties (Sequence[PropertyConfig])

  • optimizer (OptimizerConfig)

  • lr_scheduler (LRSchedulerConfig | None)

  • ignore_gpu_batch_transform_error (bool)

  • normalizers (Mapping[str, Sequence[NormalizerConfig]])

  • name (Literal['uma'])

  • model_name (str)

  • atoms_to_graph (FAIRChemAtomsToGraphSystemConfig)

  • task_name (str | None)

name: Literal['uma']

The name of the backbone model to use. Should be “uma”.

model_name: str

The specific UMA model variant to use. Options include: - “uma-s-1” - “uma-s-1.1” - “uma-m-1.1” - “uma-l”

atoms_to_graph: FAIRChemAtomsToGraphSystemConfig

Configuration for converting atomic data to graph representations.

task_name: str | None

The task name for the dataset, e.g., ‘oc20’, ‘omol’, ‘omat’, ‘odac’, ‘omc’. If None, it will be inferred from the data.

classmethod ensure_dependencies()[source]

Ensure that all dependencies are installed.

This method should raise an exception if any dependencies are missing, with a message indicating which dependencies are missing and how to install them.

create_model()[source]

Creates an instance of the finetune module for this configuration.

reset_backbone: bool

Whether to reset the backbone of the model when creating the model.

freeze_backbone: bool

Whether to freeze the backbone during training.

reset_output_heads: bool

Whether to reset the output heads of the model when creating the model.

use_pretrained_normalizers: bool

Whether to use the pretrained normalizers.

properties: Sequence[PropertyConfig]

Properties to predict.

optimizer: OptimizerConfig

Optimizer.

lr_scheduler: LRSchedulerConfig | None

Learning Rate Scheduler

ignore_gpu_batch_transform_error: bool

Whether to ignore data processing errors during training.

normalizers: Mapping[str, Sequence[NormalizerConfig]]

Normalizers for the properties.

Any property can be associated with multiple normalizers. This is useful for cases where we want to normalize the same property in different ways. For example, we may want to normalize the energy by subtracting the atomic reference energies, as well as by mean and standard deviation normalization.

The normalizers are applied in the order they are defined in the list.