mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 13:58:46 +01:00
1442677f92
* common : gpt_params_parse do not print usage * common : rework usage print (wip) * common : valign * common : rework print_usage * infill : remove cfg support * common : reorder args * server : deduplicate parameters ggml-ci * common : add missing header ggml-ci * common : remote --random-prompt usages ggml-ci * examples : migrate to gpt_params ggml-ci * batched-bench : migrate to gpt_params * retrieval : migrate to gpt_params * common : change defaults for escape and n_ctx * common : remove chatml and instruct params ggml-ci * common : passkey use gpt_params
66 lines
1.5 KiB
Bash
66 lines
1.5 KiB
Bash
#!/bin/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/gguf-split
|
|
QUANTIZE=$1/quantize
|
|
MAIN=$1/main
|
|
WORK_PATH=$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/gemma-1.1-2b-it-Q8_0-GGUF --file gemma-1.1-2b-it.Q8_0.gguf
|
|
)
|
|
echo PASS
|
|
|
|
# 2. Split model
|
|
$SPLIT --split-max-tensors 28 $WORK_PATH/gemma-1.1-2b-it.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-00006.gguf $WORK_PATH/ggml-model-requant.gguf Q4_K
|
|
echo PASS
|
|
echo
|
|
|
|
# 3a. Test the requanted model is loading properly
|
|
$MAIN --model $WORK_PATH/ggml-model-requant-00001-of-00006.gguf --n-predict 32
|
|
echo PASS
|
|
echo
|
|
|
|
# 4. Requant mode without '--keep-split'
|
|
$QUANTIZE --allow-requantize $WORK_PATH/ggml-model-split-00001-of-00006.gguf $WORK_PATH/ggml-model-requant-merge.gguf Q4_K
|
|
echo PASS
|
|
echo
|
|
|
|
# 4b. Test the requanted model is loading properly
|
|
$MAIN --model $WORK_PATH/ggml-model-requant-merge.gguf --n-predict 32
|
|
echo PASS
|
|
echo
|
|
|
|
# Clean up
|
|
rm -f $WORK_PATH/ggml-model-split*.gguf $WORK_PATH/ggml-model-requant*.gguf
|