summaryrefslogtreecommitdiff
path: root/tests/test-tokenizer-0.sh
diff options
context:
space:
mode:
Diffstat (limited to 'tests/test-tokenizer-0.sh')
-rwxr-xr-xtests/test-tokenizer-0.sh7
1 files changed, 6 insertions, 1 deletions
diff --git a/tests/test-tokenizer-0.sh b/tests/test-tokenizer-0.sh
index 2fb8632d..1fec8bbf 100755
--- a/tests/test-tokenizer-0.sh
+++ b/tests/test-tokenizer-0.sh
@@ -17,10 +17,15 @@ make -j tests/test-tokenizer-0
printf "Testing %s on %s ...\n" $name $input
+set -e
+
+printf "Tokenizing using (py) Python AutoTokenizer ...\n"
python3 ./tests/test-tokenizer-0.py ./models/tokenizers/$name --fname-tok $input > /tmp/test-tokenizer-0-$name-py.log 2>&1
-cat /tmp/test-tokenizer-0-$name-py.log | grep "tokenized in"
+printf "Tokenizing using (cpp) llama.cpp ...\n"
./tests/test-tokenizer-0 ./models/ggml-vocab-$name.gguf $input > /tmp/test-tokenizer-0-$name-cpp.log 2>&1
+
+cat /tmp/test-tokenizer-0-$name-py.log | grep "tokenized in"
cat /tmp/test-tokenizer-0-$name-cpp.log | grep "tokenized in"
diff $input.tok $input.tokcpp > /dev/null 2>&1