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

convert-hf-to-gguf-update.py

@@ -72,7 +72,7 @@ models = [
     {"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", },

convert-hf-to-gguf.py

@@ -447,7 +447,7 @@ class Model:
             # ref: https://huggingface.co/openai-community/gpt2
             res = "gpt-2"
         if chkhsh == "32d85c31273f8019248f2559fed492d929ea28b17e51d81d3bb36fff23ca72b3":
-            # ref: https://huggingface.co/stabilityai/stablelm-2-1_6b
+            # ref: https://huggingface.co/stabilityai/stablelm-2-zephyr-1_6b
             res = "stablelm2"
         if chkhsh == "6221ad2852e85ce96f791f476e0b390cf9b474c9e3d1362f53a24a06dc8220ff":
             # ref: https://huggingface.co/smallcloudai/Refact-1_6-base

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