replace with dedicated DescriptorExtractor class after refactor.

[github-actions]

For now, DPAFineTuner is reused purely as a descriptor feature extractor.

Line: 151

deepmd-kit/dpa_adapt/predictor.py

Lines 148 to 158 in a49b6f7

	DPAFineTuner,
	)
	# TODO: replace with dedicated DescriptorExtractor class after refactor.
	# For now, DPAFineTuner is reused purely as a descriptor feature extractor.
	self._extractor = DPAFineTuner(
	pretrained=self._pretrained,
	model_branch=self._model_branch,
	predictor="linear",
	pooling=self._pooling,
	type_map=self._type_map,