Skip to content

ci : use -no-cnv in gguf-split tests #11254

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.

Sign up for GitHub

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

Merged
merged 3 commits into from
Jan 15, 2025
Merged

ci : use -no-cnv in gguf-split tests #11254

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9e839a5
ci : use -no-cnv in gguf-split tests
ggerganov Jan 15, 2025
414a66f
ci : use -no-cnv in requantize tests
ggerganov Jan 15, 2025
3e794f2
scripts : fix [no ci]
ggerganov Jan 15, 2025
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
10 changes: 5 additions & 5 deletions examples/gguf-split/tests.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ echo PASS
echo

# 2b. Test the sharded model is loading properly
$MAIN --model $WORK_PATH/ggml-model-split-00001-of-00006.gguf --n-predict 32
$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-00001-of-00006.gguf --n-predict 32
echo PASS
echo

Expand All @@ -51,7 +51,7 @@ echo PASS
echo

# 3b. Test the merged model is loading properly
$MAIN --model $WORK_PATH/ggml-model-merge.gguf --n-predict 32
$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge.gguf --n-predict 32
echo PASS
echo

Expand All @@ -61,7 +61,7 @@ echo PASS
echo

# 4b. Test the sharded model is loading properly
$MAIN --model $WORK_PATH/ggml-model-split-32-tensors-00001-of-00007.gguf --n-predict 32
$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-32-tensors-00001-of-00007.gguf --n-predict 32
echo PASS
echo

Expand All @@ -71,7 +71,7 @@ echo
#echo

# 5b. Test the merged model is loading properly
#$MAIN --model $WORK_PATH/ggml-model-merge-2.gguf --n-predict 32
#$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge-2.gguf --n-predict 32
#echo PASS
#echo

Expand All @@ -81,7 +81,7 @@ echo PASS
echo

# 6b. Test the sharded model is loading properly
$MAIN --model $WORK_PATH/ggml-model-split-2G-00001-of-00002.gguf --n-predict 32
$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-2G-00001-of-00002.gguf --n-predict 32
echo PASS
echo

Expand Down
4 changes: 2 additions & 2 deletions examples/quantize/tests.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ 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
$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-00001-of-00006.gguf --n-predict 32
echo PASS
echo

Expand All @@ -57,7 +57,7 @@ echo PASS
echo

# 4b. Test the requanted model is loading properly
$MAIN --model $WORK_PATH/ggml-model-requant-merge.gguf --n-predict 32
$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-merge.gguf --n-predict 32
echo PASS
echo

Expand Down
112 changes: 0 additions & 112 deletions scripts/hf.sh
View file
Open in desktop

This file was deleted.

6 changes: 3 additions & 3 deletions tests/test-lora-conversion-inference.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,18 +80,18 @@ run_conversion_and_inference_lora() {
# Run inference
echo -e "\n\n---------------------------\n\n"
echo "Running llama-cli without lora for $model_name with hidden_size $hidden_size..."
OUTPUT_BASE=$(./llama-cli -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
OUTPUT_BASE=$(./llama-cli -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
-p "$EXPECTED_BASE_FIRST_WORD" -n 50 --seed 42 --temp 0)

echo -e "\n\n---------------------------\n\n"
echo "Running llama-cli with hot lora for $model_name with hidden_size $hidden_size..."
OUTPUT_LORA_HOT=$(./llama-cli -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
OUTPUT_LORA_HOT=$(./llama-cli -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
--lora $MODELS_REPO/$model_name/hidden_size=$hidden_size/lora/Lora-F32-LoRA.gguf \
-p "$EXPECTED_LORA_FIRST_WORD" -n 50 --seed 42 --temp 0)

echo -e "\n\n---------------------------\n\n"
echo "Running llama-cli with merged lora for $model_name with hidden_size $hidden_size..."
OUTPUT_LORA_MERGED=$(./llama-cli -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32-lora-merged.gguf \
OUTPUT_LORA_MERGED=$(./llama-cli -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32-lora-merged.gguf \
-p "$EXPECTED_LORA_FIRST_WORD" -n 50 --seed 42 --temp 0)

# Remove any initial white space
Expand Down
Loading