vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

tests : test-tokenizer-0.sh print more info (#7402)

Browse source
This commit is contained in:
Georgi Gerganov 2024-05-21 19:53:48 +03:00
parent 11474e756d
commit c3f8d58356
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
3 changed files with 9 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

9
tests/test-tokenizer-0.sh
View file

@ -17,10 +17,15 @@ make -j tests/test-tokenizer-0
printf "Testing %s on %s ...\n" $name $input
python3 ./tests/test-tokenizer-0.py ./models/tokenizers/$name --fname-tok $input > /tmp/test-tokenizer-0-$name-py.log 2>&1
cat /tmp/test-tokenizer-0-$name-py.log | grep "tokenized in"
set -e
printf "Tokenizing using (py) Python AutoTokenizer ...\n"
python3 ./tests/test-tokenizer-0.py ./models/tokenizers/$name --fname-tok $input > /tmp/test-tokenizer-0-$name-py.log 2>&1
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