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

Switch production checkpoint reference to epoch 3

Browse Source 
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.
This commit is contained in:
Joey Grasty
2026-08-30 17:28:23 -05:00
parent 57ab1fa4d5
commit 2accd43cfe
2 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
README.md
View File

@@ -24,11 +24,13 @@ The 208 training/holdout packages themselves are already embedded inside
### 1. Get the model file ### 1. Get the model file
Download `Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep2-Q8_0.gguf` (~31GB) from Download `Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf` (~31GB) from
Google Drive: Google Drive:
https://drive.google.com/open?id=1q1w_XMp6oRmfx8xqXDV-HvDx_krVxQtD https://drive.google.com/open?id=1q1w_XMp6oRmfx8xqXDV-HvDx_krVxQtD
**Note (2026-08-30): the link above still points to the ep2 file.** Production was just switched to ep3 (separability + length-calibration evidence, see `JOINT_TRAINING_CLOSEOUT_REPORT.md`); the ep3 GGUF upload and link swap are pending.
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,
@@ -51,7 +53,7 @@ This produces `llama.cpp/build/bin/llama-server`, which is what
### 3. Start the model server ### 3. Start the model server
``` ```
MODEL_PATH=/path/to/Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep2-Q8_0.gguf \ MODEL_PATH=/path/to/Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf \
LLAMA_SERVER=/path/to/llama.cpp/build/bin/llama-server \ LLAMA_SERVER=/path/to/llama.cpp/build/bin/llama-server \
./start-model.sh ./start-model.sh
``` ```

6
start-model.sh
View File

@@ -3,17 +3,17 @@
# #
# Requires: # Requires:
# - llama.cpp built with CUDA support (see README.md) # - llama.cpp built with CUDA support (see README.md)
# - the Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep2-Q8_0.gguf file (from the team # - the Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf file (from the team
# Google Drive) # Google Drive)
# #
# Configure by setting environment variables before running, e.g.: # Configure by setting environment variables before running, e.g.:
# MODEL_PATH=/data/models/Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep2-Q8_0.gguf \ # MODEL_PATH=/data/models/Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf \
# LLAMA_SERVER=/opt/llama.cpp/build/bin/llama-server \ # LLAMA_SERVER=/opt/llama.cpp/build/bin/llama-server \
# ./start-model.sh # ./start-model.sh
# or just edit the defaults below. # or just edit the defaults below.
set -e set -e
MODEL_PATH="${MODEL_PATH:-$HOME/models/Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep2-Q8_0.gguf}" MODEL_PATH="${MODEL_PATH:-$HOME/models/Qwen3-30B-A3B-VoxDay-Nuttall-SFT-ep3-Q8_0.gguf}"
LLAMA_SERVER="${LLAMA_SERVER:-$HOME/llama.cpp/build/bin/llama-server}" LLAMA_SERVER="${LLAMA_SERVER:-$HOME/llama.cpp/build/bin/llama-server}"
HOST="${HOST:-0.0.0.0}" HOST="${HOST:-0.0.0.0}"
PORT="${PORT:-8200}" PORT="${PORT:-8200}"