jungfrauandClaude Fable 5.1
5bcb6d993d
CI / ledger-and-tools (push) Successful in 21s
--skip-train registers the version with the day it runs, so the nano and the yolo26s of cycle 5 existed twice in the registry (2026-10-23 and 2026-10-25); the runs point at the 10-25 ones, the others are removed. A run whose base weights are a registry version (the warm start) was named after the file weights.pt; it is now named after that version's family. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013uu3Bxsu5JqFhaWa9Ftu6z
Model Registry
Each trained model lives in its own versioned subdirectory:
models/registry/<version-id>/
├── weights.pt ← primary PyTorch checkpoint
├── exports/ ← derived export formats
│ ├── model.onnx
│ ├── model.engine ← TensorRT (hardware-specific, gitignored)
│ └── pruned_weights.pt
└── metadata.json ← version info and metrics
Naming convention
<architecture>-<task>-<variant>-<YYYY-MM-DD>
Examples:
yolo26n-seg-overlap-false-2026-04-12— yolo26n, segmentation, overlap_mask=False, trained 2026-04-12yolo26n-seg-multiscale-2026-03-16— yolo26n, segmentation, multi-scale training
metadata.json schema
| Field | Description |
|---|---|
model_id |
Same as directory name |
family |
Base architecture (e.g. yolo26n) |
task |
segmentation, detection, etc. |
training_date |
ISO date of training run |
export_formats |
List of available formats |
metrics |
mAP, precision, recall, etc. |
Active production model
See models/active/production.json for the currently deployed version.