Nibmeister/voice-bench
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add scale-up SFT model Drive links to the README

Browse Source 
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>
This commit is contained in:
Joey Grasty
2026-09-02 17:26:25 -05:00
parent a8068b095d
commit ef5792256c
1 changed files with 15 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
README.md
View File

@@ -30,17 +30,25 @@ out.
### 1. Get the model file ### 1. Get the model file
Two candidate checkpoints are available. Separability and length-calibration Four candidate checkpoints are available, across two SFT rounds on the same
metrics lean slightly toward epoch 3 (see `JOINT_TRAINING_CLOSEOUT_REPORT.md` joint CPT base: the original 208-package SFT, and a newer 433-package
for the numbers), but not decisively enough to settle it on metrics alone — scale-up SFT trained on eight additional untrained books (see the Book
**live testing through `voice-bench.html` is what should decide between dropdown in `voice-bench.html`). Within each round, separability and
them.** Download both, run one at a time (or both at once on different length-calibration metrics lean slightly toward epoch 3, but not decisively
ports — see step 3), and compare generations on real held-out packages enough to settle it on metrics alone — **live testing through
before picking one. `voice-bench.html` is what should decide between them**, both within a
round and between the original and scale-up rounds. Download whichever
you're comparing, run one at a time (or several at once on different
ports — see step 3).
Original SFT:
- `Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf` (~31GB): https://drive.google.com/open?id=1QZT488Uu1b9Pxoie9Hs2lnxtOhMD4Pwr - `Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf` (~31GB): https://drive.google.com/open?id=1QZT488Uu1b9Pxoie9Hs2lnxtOhMD4Pwr
- `Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep2-Q8_0.gguf` (~31GB): https://drive.google.com/open?id=1q1w_XMp6oRmfx8xqXDV-HvDx_krVxQtD - `Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep2-Q8_0.gguf` (~31GB): https://drive.google.com/open?id=1q1w_XMp6oRmfx8xqXDV-HvDx_krVxQtD
Scale-up SFT:
- `Qwen3-30B-A3B-VoxDay-Nuttall-SFT-Scaleup-ep3-Q8_0.gguf` (~31GB): https://drive.google.com/open?id=1nreKTn2JnEtQO2ydrCg8uOJbxcuOIQRO
- `Qwen3-30B-A3B-VoxDay-Nuttall-SFT-Scaleup-ep2-Q8_0.gguf` (~31GB): https://drive.google.com/open?id=1xHeXjLrQyvd_Mey1EvgCz6raeAxJJFzG
Memory needed: ~31GB for the weights plus ~3GB of KV cache at the full Memory needed: ~31GB for the weights plus ~3GB of KV cache at the full
32768-token context, so ~35GB total. Confirmed working on a DGX Spark; 32768-token context, so ~35GB total. Confirmed working on a DGX Spark;
should comfortably fit a 48GB L40 as well. If a machine has less than that, should comfortably fit a 48GB L40 as well. If a machine has less than that,