Hi IBM/MoLFormer maintainers,
I am trying to reproduce the BBBP split used by the MoLFormer/MoleculeNet fine-tuning path so we can run a clean external anchor against the public MAMMAL BBBP checkpoint:
- model:
ibm-research/biomed.omics.bl.sm.ma-ted-458m.moleculenet_bbbp
- model revision:
4f249585b27907f0b5f191dba87cf3ecf2c23ef5
- needed split:
data/bbbp/test.csv from finetune_datasets.zip
The current README points to:
https://ibm.box.com/v/MoLFormer-data
That URL currently returns HTTP/2 404 from our environment. The README still describes the expected finetune_datasets.zip hierarchy, including:
data/
bbbp/
test.csv
train.csv
valid.csv
Could you provide one of the following?
- A working public URL for
finetune_datasets.zip.
- The canonical
data/bbbp/test.csv split used for the published MoLFormer MoleculeNet BBBP evaluation.
- A checksum or commit/source reference that lets downstream reviewers verify the split identity.
We are intentionally not substituting a third-party BBBP mirror because the review target is the canonical MoLFormer predefined split.
Contact: saul@projecttfb.com
Thank you.
Hi IBM/MoLFormer maintainers,
I am trying to reproduce the BBBP split used by the MoLFormer/MoleculeNet fine-tuning path so we can run a clean external anchor against the public MAMMAL BBBP checkpoint:
ibm-research/biomed.omics.bl.sm.ma-ted-458m.moleculenet_bbbp4f249585b27907f0b5f191dba87cf3ecf2c23ef5data/bbbp/test.csvfromfinetune_datasets.zipThe current README points to:
https://ibm.box.com/v/MoLFormer-dataThat URL currently returns
HTTP/2 404from our environment. The README still describes the expectedfinetune_datasets.ziphierarchy, including:Could you provide one of the following?
finetune_datasets.zip.data/bbbp/test.csvsplit used for the published MoLFormer MoleculeNet BBBP evaluation.We are intentionally not substituting a third-party BBBP mirror because the review target is the canonical MoLFormer predefined split.
Contact: saul@projecttfb.com
Thank you.