mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-28 08:31:25 +00:00
66 lines
1.6 KiB
Bash
66 lines
1.6 KiB
Bash
#!/usr/bin/env bash
|
|
|
|
set -eu
|
|
|
|
if [ $# -lt 1 ]
|
|
then
|
|
echo "usage: $0 path_to_build_binary [path_to_temp_folder]"
|
|
echo "example: $0 ../../build/bin ../../tmp"
|
|
exit 1
|
|
fi
|
|
|
|
if [ $# -gt 1 ]
|
|
then
|
|
TMP_DIR=$2
|
|
else
|
|
TMP_DIR=/tmp
|
|
fi
|
|
|
|
set -x
|
|
|
|
SPLIT=$1/llama-gguf-split
|
|
QUANTIZE=$1/llama-quantize
|
|
MAIN=$1/llama-cli
|
|
WORK_PATH=$TMP_DIR/quantize
|
|
ROOT_DIR=$(realpath $(dirname $0)/../../)
|
|
|
|
mkdir -p "$WORK_PATH"
|
|
|
|
# Clean up in case of previously failed test
|
|
rm -f $WORK_PATH/ggml-model-split*.gguf $WORK_PATH/ggml-model-requant*.gguf
|
|
|
|
# 1. Get a model
|
|
(
|
|
cd $WORK_PATH
|
|
"$ROOT_DIR"/scripts/hf.sh --repo ggml-org/Qwen3-0.6B-GGUF --file Qwen3-0.6B-Q8_0.gguf
|
|
)
|
|
echo PASS
|
|
|
|
# 2. Split model
|
|
$SPLIT --split-max-tensors 28 $WORK_PATH/Qwen3-0.6B-Q8_0.gguf $WORK_PATH/ggml-model-split
|
|
echo PASS
|
|
echo
|
|
|
|
# 3. Requant model with '--keep-split'
|
|
$QUANTIZE --allow-requantize --keep-split $WORK_PATH/ggml-model-split-00001-of-00012.gguf $WORK_PATH/ggml-model-requant.gguf Q4_K
|
|
echo PASS
|
|
echo
|
|
|
|
# 3a. Test the requanted model is loading properly
|
|
$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-00001-of-00012.gguf -p "I believe the meaning of life is" --n-predict 32
|
|
echo PASS
|
|
echo
|
|
|
|
# 4. Requant mode without '--keep-split'
|
|
$QUANTIZE --allow-requantize $WORK_PATH/ggml-model-split-00001-of-00012.gguf $WORK_PATH/ggml-model-requant-merge.gguf Q4_K
|
|
echo PASS
|
|
echo
|
|
|
|
# 4b. Test the requanted model is loading properly
|
|
$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-merge.gguf -p "I believe the meaning of life is" --n-predict 32
|
|
echo PASS
|
|
echo
|
|
|
|
# Clean up
|
|
rm -f $WORK_PATH/ggml-model-split*.gguf $WORK_PATH/ggml-model-requant*.gguf
|