llama.cpp verification source 2026-05-22

tests/test-tokenizer-0.sh

@@ -0,0 +1,46 @@
+#!/usr/bin/env bash
+#
+# Usage:
+#
+#   test-tokenizer-0.sh <name> <input>
+#
+
+if [ $# -ne 2 ]; then
+    printf "Usage: $0 <name> <input>\n"
+    exit 1
+fi
+
+name=$1
+input=$2
+
+# Build using CMake if binary doesn't exist
+if [ ! -f ./build/bin/test-tokenizer-0 ]; then
+    printf "Building test-tokenizer-0 with CMake...\n"
+    cmake -B build -DLLAMA_BUILD_TESTS=ON
+    cmake --build build --target test-tokenizer-0 -j
+fi
+
+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
+
+printf "Tokenizing using (cpp) llama.cpp ...\n"
+./build/bin/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"
+
+set +e
+
+diff $input.tok $input.tokcpp > /dev/null 2>&1
+
+if [ $? -eq 0 ]; then
+    printf "Tokenization is correct!\n"
+else
+    diff $input.tok $input.tokcpp | head -n 32
+
+    printf "Tokenization differs!\n"
+fi