Both Qwen3-30B-A3B-VoxDay-Nuttall-SFT-Scaleup-ep2/ep3 GGUFs are now
uploaded to the same Byron_AI_LLMs Drive folder as the original ep2/ep3
checkpoints, for live-testing comparison between the two SFT rounds.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Merge the 433-package scale-up SFT (8 additional untrained books) into
the existing 208-package browser, tagged with book title and normalized
train/holdout split. Add a Book dropdown per author, with a badge on
each package showing which book it came from.
Also fixes chapter grouping/ordering for the new books:
- Vox Day: split POV-name chapter labels when the same character
recurs across separate, non-adjacent chapters (detected via the
pipeline's own STORY segmentation resets), ordered by book_region
as a coarse book-order approximation.
- Nuttall: sort spelled-out chapter numbers ("Chapter-Twenty-Three")
numerically instead of alphabetically.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Metrics lean toward ep3 but aren't decisive enough to call it outright.
README now presents both checkpoints as candidates and walks through
running them side-by-side (different ports) for direct comparison in
voice-bench.html, rather than naming one as current production.
ep3 uploaded to the team Drive folder and linked as the current
production checkpoint. ep2's link is kept in place per request, labeled
as the previous production checkpoint rather than removed.
Production was switched from ep2 to ep3 based on separability and
length-calibration evidence (JOINT_TRAINING_CLOSEOUT_REPORT.md). Updates
start-model.sh's default and the README's setup instructions. The Drive
link itself still points to the ep2 file pending re-upload -- flagged
inline in the README.
Self-contained browser tool for exploring the Vox Day / Nuttall SFT
packages and generating scenes against the joint CPT+SFT model, plus a
portable launch script (start-model.sh) and setup README for running
the model server on a fresh machine (DGX Spark or CUDA/L40 box).
