Download edits/input_reference_mask_v20.json from wasarou/weight-space-programming-boltz2: direct link, hf CLI and curl.
- Browser
- Download file 815 Bytes
-
https://huggingface.co/wasarou/weight-space-programming-boltz2/resolve/main/edits/input_reference_mask_v20.json
- Command line
-
hf download hf://wasarou/weight-space-programming-boltz2/edits/input_reference_mask_v20.json
-
curl -L -o input_reference_mask_v20.json https://huggingface.co/wasarou/weight-space-programming-boltz2/resolve/main/edits/input_reference_mask_v20.json
815 Bytes
| { | |
| "name": "input_reference_mask_v20", | |
| "method": "Reasoning-driven direct weight-space programming without training", | |
| "hypothesis": "The input atom encoder mixes atoms from multiple reference spaces inside attention windows. Its learned same-reference mask distinguishes atoms of one ligand or one protein residue. Double this existing mask embedding to test whether a stronger indication of shared reference space helps the encoder combine local vectors into a handedness signal. Scaling an embedding does not guarantee a uniform increase in attention, so the effect remains empirical.", | |
| "evidence": ["artifacts/pair_weight_inspection.json", "artifacts/prediction_reference_parity.analysis.json"], | |
| "operations": [ | |
| {"key": "input_embedder.atom_encoder.embed_atompair_mask.weight", "factor": 2.0} | |
| ] | |
| } | |