cellmap_flow.models.configs.huggingface

HuggingFaceModelConfig: a cellmap_models export on the Hugging Face Hub.

It is the export at the repository’s root, downloaded (download_export), then built as a CellMapModelConfig. to_dict() adds the repo’s metadata.json for the pipeline builder; building a launch command never downloads it.

Attributes

logger

Classes

HuggingFaceModelConfig

Configuration class for a Hugging Face model.

Functions

download_export(repo[, revision])

The cellmap_models export at the root of the Hugging Face repository

Module Contents

cellmap_flow.models.configs.huggingface.logger

cellmap_flow.models.configs.huggingface.download_export(repo, revision=None)

The cellmap_models export at the root of the Hugging Face repository repo, downloaded: its CellmapModel.

The root’s files only. A model a server published (dashboard/routes/finetune/publish.py) has its ONNX web export in a folder beside them, a model of its own (<repo>/<folder>, type onnx) whose files are of no use here and can be gigabytes.

class cellmap_flow.models.configs.huggingface.HuggingFaceModelConfig(repo, revision=None, name=None, scale=None)

Configuration class for a Hugging Face model.

cli_name = 'huggingface'

finetunable = True

METADATA_RETRY_SECONDS = 60

repo

revision = None

name = None

scale = None

finetune_modes(): export_finetune_modes of the repo’s files. Their list is asked for, not the model, once for the life of this config; when the Hub cannot say, both are offered, and the job says which it takes.

declared_geometry(): Its metadata.json’s, as a cellmap export’s (metadata_geometry): that file is downloaded, not the model.

declared_input_norm(data_range=None): The input normalization the repo’s metadata.json declares: its input_norm, cellmap-flow steps, which a model a server published has (finetune.export_web); else a cellmap-models export’s input_normalization, the range the model reads (metadata_input_norm), for raw data spanning data_range. Downloaded as for declared_geometry; cheap after the first ask, as _load_metadata is, and never raises.

to_dict(): This config as a model entry, which registry.build_model rebuilds.