From 7ac0b36ae6521addef1469eeb844c53200a3934b Mon Sep 17 00:00:00 2001 From: Joey Grasty Date: Sun, 30 Aug 2026 19:23:12 -0500 Subject: [PATCH] Frame epoch 2 vs epoch 3 as a live-testing decision, not a settled pick 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. --- README.md | 32 ++++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index c01930c..984ed1b 100644 --- a/README.md +++ b/README.md @@ -24,17 +24,16 @@ The 208 training/holdout packages themselves are already embedded inside ### 1. Get the model file -Download `Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf` (~31GB) from -Google Drive — **this is the current production checkpoint**, switched from -ep2 on 2026-08-30 based on separability and length-calibration evidence -(see `JOINT_TRAINING_CLOSEOUT_REPORT.md`): +Two candidate checkpoints are available. Separability and length-calibration +metrics lean slightly toward epoch 3 (see `JOINT_TRAINING_CLOSEOUT_REPORT.md` +for the numbers), but not decisively enough to settle it on metrics alone — +**live testing through `voice-bench.html` is what should decide between +them.** Download both, run one at a time (or both at once on different +ports — see step 3), and compare generations on real held-out packages +before picking one. -https://drive.google.com/open?id=1QZT488Uu1b9Pxoie9Hs2lnxtOhMD4Pwr - -The previous production checkpoint, `Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep2-Q8_0.gguf`, -remains available for comparison: - -https://drive.google.com/open?id=1q1w_XMp6oRmfx8xqXDV-HvDx_krVxQtD +- `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 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; @@ -57,6 +56,8 @@ This produces `llama.cpp/build/bin/llama-server`, which is what ### 3. Start the model server +Point `MODEL_PATH` at whichever checkpoint you're testing: + ``` MODEL_PATH=/path/to/Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf \ LLAMA_SERVER=/path/to/llama.cpp/build/bin/llama-server \ @@ -67,6 +68,17 @@ Leave this running in a terminal — it's the process `voice-bench.html` talks to. If you'd rather not set environment variables every time, edit the defaults at the top of `start-model.sh` instead. +**To compare epoch 2 and epoch 3 directly**, run both at once on different +ports (memory permitting — see below): + +``` +MODEL_PATH=/path/to/Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep2-Q8_0.gguf PORT=8200 ./start-model.sh +MODEL_PATH=/path/to/Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf PORT=8201 ./start-model.sh +``` + +then switch `voice-bench.html`'s "Server" field between `:8200` and `:8201` +on the same packet to compare their generations side by side. + ### 4. Open voice-bench.html Open the file in a browser. The "Server" field in the top-right corner