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

teleprint-me · May 23, 2024 · d17d582 · d17d582
1 parent f3ddffe
commit d17d582
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 2 deletions.
diff --git a/convert-hf-to-gguf-update.py b/convert-hf-to-gguf-update.py
@@ -72,7 +72,7 @@ class TOKENIZER_TYPE(IntEnum):
     {"name": "mpt",            "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/mosaicml/mpt-7b", },
     {"name": "starcoder",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/bigcode/starcoder2-3b", },
     {"name": "gpt-2",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/openai-community/gpt2", },
-    {"name": "stablelm",       "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b", },
+    {"name": "stablelm2",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b", },
     {"name": "refact",         "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/smallcloudai/Refact-1_6-base", },
     {"name": "command-r",      "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/CohereForAI/c4ai-command-r-v01", },
     {"name": "qwen2",          "tokt": TOKENIZER_TYPE.BPE, "repo": "https://huggingface.co/Qwen/Qwen1.5-7B", },

diff --git 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