From c3f8d583560b4f261fa21c976793e538c60cd66c Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Tue, 21 May 2024 19:53:48 +0300 Subject: tests : test-tokenizer-0.sh print more info (#7402) --- tests/test-tokenizer-0.sh | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'tests') 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 -- cgit v1.2.3