From cc66a7f78f95dcb5208420f4dd1abc3fc6aec0cc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sigbj=C3=B8rn=20Skj=C3=A6ret?= <sigbjorn.skjaeret@scala.com>
Date: Wed, 11 Jun 2025 17:16:32 +0200
Subject: [PATCH] tests : add test-tokenizers-repo (#14017)

---
 tests/CMakeLists.txt          | 38 +++++++++++++++++++++++++++++++++--
 tests/test-tokenizers-repo.sh | 36 +++++++++++++++++++++++++++++++++
 2 files changed, 72 insertions(+), 2 deletions(-)
 create mode 100755 tests/test-tokenizers-repo.sh

diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt
index 2f7bad2cf..85299837c 100644
--- a/tests/CMakeLists.txt
+++ b/tests/CMakeLists.txt
@@ -42,6 +42,34 @@ function(llama_test target)
     set_property(TEST ${TEST_NAME} PROPERTY LABELS ${LLAMA_TEST_LABEL})
 endfunction()
 
+function(llama_test_cmd target)
+    include(CMakeParseArguments)
+    set(options)
+    set(oneValueArgs NAME LABEL WORKING_DIRECTORY)
+    set(multiValueArgs ARGS)
+    cmake_parse_arguments(LLAMA_TEST "${options}" "${oneValueArgs}" "${multiValueArgs}" ${ARGN})
+
+    if (NOT DEFINED LLAMA_TEST_LABEL)
+        set(LLAMA_TEST_LABEL "main")
+    endif()
+    if (NOT DEFINED LLAMA_TEST_WORKING_DIRECTORY)
+        set(LLAMA_TEST_WORKING_DIRECTORY .)
+    endif()
+    if (DEFINED LLAMA_TEST_NAME)
+        set(TEST_NAME ${LLAMA_TEST_NAME})
+    else()
+        set(TEST_NAME ${target})
+    endif()
+
+    add_test(
+        NAME ${TEST_NAME}
+        WORKING_DIRECTORY ${LLAMA_TEST_WORKING_DIRECTORY}
+        COMMAND ${target}
+        ${LLAMA_TEST_ARGS})
+
+    set_property(TEST ${TEST_NAME} PROPERTY LABELS ${LLAMA_TEST_LABEL})
+endfunction()
+
 # Builds and runs a test source file.
 # Optional args:
 # - NAME: name of the executable & test target (defaults to the source file name without extension)
@@ -97,8 +125,14 @@ llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2             ARGS ${CMAKE
 llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact            ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf)
 llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder         ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-starcoder.gguf)
 
-# TODO: missing HF tokenizer for this model in convert_hf_to_gguf_update.py, see https://github.com/ggml-org/llama.cpp/pull/13847
-# llama_test(test-tokenizer-0 NAME test-tokenizer-0-nomic-bert-moe    ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-nomic-bert-moe.gguf)
+if (NOT WIN32)
+    llama_test_cmd(
+        ${CMAKE_CURRENT_SOURCE_DIR}/test-tokenizers-repo.sh
+        NAME test-tokenizers-ggml-vocabs
+        WORKING_DIRECTORY ${CMAKE_RUNTIME_OUTPUT_DIRECTORY}
+        ARGS https://huggingface.co/ggml-org/vocabs ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocabs
+    )
+endif()
 
 if (LLAMA_LLGUIDANCE)
     llama_build_and_test(test-grammar-llguidance.cpp ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama-bpe.gguf)
diff --git a/tests/test-tokenizers-repo.sh b/tests/test-tokenizers-repo.sh
new file mode 100755
index 000000000..86e839133
--- /dev/null
+++ b/tests/test-tokenizers-repo.sh
@@ -0,0 +1,36 @@
+#!/bin/bash
+
+if [ $# -lt 2 ]; then
+    printf "Usage: $0 <git-repo> <target-folder> [<test-exe>]\n"
+    exit 1
+fi
+
+if [ $# -eq 3 ]; then
+    toktest=$3
+else
+    toktest="./test-tokenizer-0"
+fi
+
+if [ ! -x $toktest ]; then
+    printf "Test executable \"$toktest\" not found!\n"
+    exit 1
+fi
+
+repo=$1
+folder=$2
+
+if [ -d $folder ] && [ -d $folder/.git ]; then
+    (cd $folder; git pull)
+else
+    git clone $repo $folder
+fi
+
+shopt -s globstar
+for gguf in $folder/**/*.gguf; do
+    if [ -f $gguf.inp ] && [ -f $gguf.out ]; then
+        $toktest $gguf
+    else
+        printf "Found \"$gguf\" without matching inp/out files, ignoring...\n"
+    fi
+done
+