Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fix --split-max-size #6655

Merged
merged 7 commits into from
Apr 14, 2024
Merged
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
add tests.sh
  • Loading branch information
CISC authored Apr 13, 2024
commit 6738215a10bd4d128357b264eba1382303ef26ba
81 changes: 81 additions & 0 deletions examples/gguf-split/tests.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,81 @@
#!/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
MAIN=$1/main
WORK_PATH=$TMP_DIR
CUR_DIR=$(pwd)

# 1. Get a model
(
cd $WORK_PATH
"$CUR_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 with max tensors strategy
$SPLIT --split-max-tensors 28 $WORK_PATH/gemma-1.1-2b-it.Q8_0.gguf $WORK_PATH/ggml-model-split
echo PASS
echo

# 2b. Test the sharded model is loading properly
$MAIN --model $WORK_PATH/ggml-model-split-00001-of-00006.gguf --random-prompt --n-predict 32
echo PASS
echo

# 3. Merge
$SPLIT --merge $WORK_PATH/ggml-model-split-00001-of-00006.gguf $WORK_PATH/ggml-model-merge.gguf
echo PASS
echo

# 3b. Test the merged model is loading properly
$MAIN --model $WORK_PATH/ggml-model-merge.gguf --random-prompt --n-predict 32
echo PASS
echo

# 4. Split with no tensor in metadata
#$SPLIT --split-max-tensors 32 --no-tensor-in-metadata $WORK_PATH/ggml-model-merge.gguf $WORK_PATH/ggml-model-split-32-tensors
#echo PASS
#echo

# 4b. Test the sharded model is loading properly
#$MAIN --model $WORK_PATH/ggml-model-split-32-tensors-00001-of-00006.gguf --random-prompt --n-predict 32
#echo PASS
#echo

# 5. Merge
#$SPLIT --merge $WORK_PATH/ggml-model-split-32-tensors-00001-of-00006.gguf $WORK_PATH/ggml-model-merge-2.gguf
#echo PASS
#echo

# 5b. Test the merged model is loading properly
#$MAIN --model $WORK_PATH/ggml-model-merge-2.gguf --random-prompt --n-predict 32
#echo PASS
#echo

# 6. Split with size strategy
$SPLIT --split-max-size 2G $WORK_PATH/ggml-model-merge.gguf $WORK_PATH/ggml-model-split-2G
echo PASS
echo

# 6b. Test the sharded model is loading properly
$MAIN --model $WORK_PATH/ggml-model-split-2G-00001-of-00002.gguf --random-prompt --n-predict 32
echo PASS
echo
Loading