tests : add test-tokenizers-repo (#14017)

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
+