5 days ago
-
3D full finetuning: NDHWC train_graph.json + torch_params.json, structured weight_map to_onnx, 3D runtime; 2D spike peak_mb corrected
6 days ago
-
finetune runtime: note on Blob import (HF serves .js as non-JS MIME)
-
Browser finetuning: manifest finetune block (head; full/tfjs for 2D students), initializer offsets, weight maps, torch_version/exporter/opset, source_repo for 2D students
7 days ago
-
2D students: final 60k-step weights (val F1 0.883 setup_53_2d, 0.902 setup_54_2d)
-
2D students to top-level setup_53_2d/ setup_54_2d/ (3D manifest schema, per-axis sizes, step 20000); source_repo on 3D manifests; remove 2d/
