lucasoc
/

sci-image-models

vision-language

table-extraction

scientific-figures

icdar-metric-loss

Model card Files Files and versions

sci-image-models / src /training /__init__.py

lucasoc's picture

feat: initial release of sci-image-markdown Qwen2.5-VL-3B LoRA adapter and extraction codebase

be90b31 verified 17 days ago

Raw History Blame Contribute Delete

179 Bytes

	"""
	Training pipeline modules.
	"""

	from .trainer import SciImageTableTrainer, build_training_arguments

	__all__ = [
	"SciImageTableTrainer",
	"build_training_arguments",
	]