Add scale-up SFT packages and fix chapter browsing/ordering
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>
This commit is contained in:
10
README.md
10
README.md
@@ -17,8 +17,14 @@ https://claude.ai/code/artifact/d3415f56-3f9b-40de-aa70-ac0992549ced
|
|||||||
[llama.cpp](https://github.com/ggml-org/llama.cpp)) that `voice-bench.html`
|
[llama.cpp](https://github.com/ggml-org/llama.cpp)) that `voice-bench.html`
|
||||||
sends generation requests to.
|
sends generation requests to.
|
||||||
|
|
||||||
The 208 training/holdout packages themselves are already embedded inside
|
All 641 training/holdout packages across both SFT rounds are already
|
||||||
`voice-bench.html` — nothing else needs downloading for browsing.
|
embedded inside `voice-bench.html` — nothing else needs downloading for
|
||||||
|
browsing. That's the original 208-package SFT (one book per author: *A Sea
|
||||||
|
of Skulls*, *Hour of the Wolf*) plus the 433-package scale-up SFT (four
|
||||||
|
more books per author, all held out of both CPT and the original SFT). Use
|
||||||
|
the **Book** dropdown to switch between them; each package's card also
|
||||||
|
shows which book it came from and whether it was used in training or held
|
||||||
|
out.
|
||||||
|
|
||||||
## One-time setup (per machine)
|
## One-time setup (per machine)
|
||||||
|
|
||||||
|
|||||||
986
voice-bench.html
986
voice-bench.html
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user