Which Approach is recommended for Fine-Tuning Molecular Property Prediction

I am working on fine-tuning uni-mol for predicting molecular properties and have noticed an inconsistency in the data processing methods provided in the repository. There are some **small differences** between the [smi2_3Dcoords](https://github.com/dptech-corp/Uni-Mol/blob/37c6ddc4a3f263b8885cd3fba2faebb5d0bef9f7/unimol/notebooks/unimol_mol_property_demo.ipynb) function in the example notebook and the [inner_smi2coords](https://github.com/dptech-corp/Uni-Mol/blob/37c6ddc4a3f263b8885cd3fba2faebb5d0bef9f7/unimol_tools/unimol_tools/data/conformer.py#L100) function in the conformer.py file within the MolTrain class for unimol_tools.

So, which approach is more recommended for fine-tuning unimol for molecular property prediction — example jupyter notebook or the MolTrain in unimol_tools ?

Best regards,