ci : use smaller model (#16168)

* ci : switch from gemma to qwen3 0.6b

* ci : use smaller model for some tests

ci/run.sh

@@ -210,33 +210,9 @@ function gg_sum_ctest_release {
     gg_printf '```\n'
 }
 
-# test_scripts_debug
+# test_scripts
 
-function gg_run_test_scripts_debug {
-    cd ${SRC}
-
-    set -e
-
-    (cd ./tools/gguf-split && time bash tests.sh "$SRC/build-ci-debug/bin" "$MNT/models") 2>&1 | tee -a $OUT/${ci}-scripts.log
-    (cd ./tools/quantize   && time bash tests.sh "$SRC/build-ci-debug/bin" "$MNT/models") 2>&1 | tee -a $OUT/${ci}-scripts.log
-
-    set +e
-}
-
-function gg_sum_test_scripts_debug {
-    gg_printf '### %s\n\n' "${ci}"
-
-    gg_printf 'Runs test scripts in debug mode\n'
-    gg_printf '- status: %s\n' "$(cat $OUT/${ci}.exit)"
-    gg_printf '```\n'
-    gg_printf '%s\n' "$(cat $OUT/${ci}-scripts.log)"
-    gg_printf '```\n'
-    gg_printf '\n'
-}
-
-# test_scripts_release
-
-function gg_run_test_scripts_release {
+function gg_run_test_scripts {
     cd ${SRC}
 
     set -e
@@ -247,10 +223,10 @@ function gg_run_test_scripts_release {
     set +e
 }
 
-function gg_sum_test_scripts_release {
+function gg_sum_test_scripts {
     gg_printf '### %s\n\n' "${ci}"
 
-    gg_printf 'Runs test scripts in release mode\n'
+    gg_printf 'Runs test scripts\n'
     gg_printf '- status: %s\n' "$(cat $OUT/${ci}.exit)"
     gg_printf '```\n'
     gg_printf '%s\n' "$(cat $OUT/${ci}-scripts.log)"
@@ -627,8 +603,7 @@ if [ -z ${GG_BUILD_LOW_PERF} ]; then
     test $ret -eq 0 && gg_run rerank_tiny
 
     if [ -z ${GG_BUILD_CLOUD} ] || [ ${GG_BUILD_EXTRA_TESTS_0} ]; then
-        test $ret -eq 0 && gg_run test_scripts_debug
-        test $ret -eq 0 && gg_run test_scripts_release
+        test $ret -eq 0 && gg_run test_scripts
     fi
 
     test $ret -eq 0 && gg_run qwen3_0_6b

tools/gguf-split/tests.sh

@@ -31,27 +31,27 @@ rm -f $WORK_PATH/ggml-model-split*.gguf $WORK_PATH/ggml-model-merge*.gguf
 # 1. Get a model
 (
 cd $WORK_PATH
-"$ROOT_DIR"/scripts/hf.sh --repo ggml-org/gemma-1.1-2b-it-Q8_0-GGUF --file gemma-1.1-2b-it.Q8_0.gguf
+"$ROOT_DIR"/scripts/hf.sh --repo ggml-org/Qwen3-0.6B-GGUF --file Qwen3-0.6B-Q8_0.gguf
 )
 echo PASS
 
 # 2. Split with max tensors strategy
-$SPLIT --split-max-tensors 28  $WORK_PATH/gemma-1.1-2b-it.Q8_0.gguf $WORK_PATH/ggml-model-split
+$SPLIT --split-max-tensors 28  $WORK_PATH/Qwen3-0.6B-Q8_0.gguf $WORK_PATH/ggml-model-split
 echo PASS
 echo
 
 # 2b. Test the sharded model is loading properly
-$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-00001-of-00006.gguf --n-predict 32
+$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-00001-of-00012.gguf -p "I believe the meaning of life is" --n-predict 32
 echo PASS
 echo
 
 # 3. Merge
-$SPLIT --merge $WORK_PATH/ggml-model-split-00001-of-00006.gguf $WORK_PATH/ggml-model-merge.gguf
+$SPLIT --merge $WORK_PATH/ggml-model-split-00001-of-00012.gguf $WORK_PATH/ggml-model-merge.gguf
 echo PASS
 echo
 
 # 3b. Test the merged model is loading properly
-$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge.gguf --n-predict 32
+$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge.gguf -p "I believe the meaning of life is" --n-predict 32
 echo PASS
 echo
 
@@ -61,12 +61,12 @@ echo PASS
 echo
 
 # 4b. Test the sharded model is loading properly
-$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-32-tensors-00001-of-00007.gguf --n-predict 32
+$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-32-tensors-00001-of-00011.gguf -p "I believe the meaning of life is" --n-predict 32
 echo PASS
 echo
 
 # 5. Merge
-#$SPLIT --merge $WORK_PATH/ggml-model-split-32-tensors-00001-of-00006.gguf $WORK_PATH/ggml-model-merge-2.gguf
+#$SPLIT --merge $WORK_PATH/ggml-model-split-32-tensors-00001-of-00012.gguf $WORK_PATH/ggml-model-merge-2.gguf
 #echo PASS
 #echo
 
@@ -76,12 +76,12 @@ echo
 #echo
 
 # 6. Split with size strategy
-$SPLIT --split-max-size 2G $WORK_PATH/ggml-model-merge.gguf $WORK_PATH/ggml-model-split-2G
+$SPLIT --split-max-size 500M $WORK_PATH/ggml-model-merge.gguf $WORK_PATH/ggml-model-split-500M
 echo PASS
 echo
 
 # 6b. Test the sharded model is loading properly
-$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-2G-00001-of-00002.gguf --n-predict 32
+$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-500M-00001-of-00002.gguf -p "I believe the meaning of life is" --n-predict 32
 echo PASS
 echo
 

tools/quantize/tests.sh

@@ -32,32 +32,32 @@ rm -f $WORK_PATH/ggml-model-split*.gguf $WORK_PATH/ggml-model-requant*.gguf
 # 1. Get a model
 (
 cd $WORK_PATH
-"$ROOT_DIR"/scripts/hf.sh --repo ggml-org/gemma-1.1-2b-it-Q8_0-GGUF --file gemma-1.1-2b-it.Q8_0.gguf
+"$ROOT_DIR"/scripts/hf.sh --repo ggml-org/Qwen3-0.6B-GGUF --file Qwen3-0.6B-Q8_0.gguf
 )
 echo PASS
 
 # 2. Split model
-$SPLIT --split-max-tensors 28  $WORK_PATH/gemma-1.1-2b-it.Q8_0.gguf $WORK_PATH/ggml-model-split
+$SPLIT --split-max-tensors 28  $WORK_PATH/Qwen3-0.6B-Q8_0.gguf $WORK_PATH/ggml-model-split
 echo PASS
 echo
 
 # 3. Requant model with '--keep-split'
-$QUANTIZE --allow-requantize --keep-split $WORK_PATH/ggml-model-split-00001-of-00006.gguf $WORK_PATH/ggml-model-requant.gguf Q4_K
+$QUANTIZE --allow-requantize --keep-split $WORK_PATH/ggml-model-split-00001-of-00012.gguf $WORK_PATH/ggml-model-requant.gguf Q4_K
 echo PASS
 echo
 
 # 3a. Test the requanted model is loading properly
-$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-00001-of-00006.gguf --n-predict 32
+$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-00001-of-00012.gguf -p "I believe the meaning of life is" --n-predict 32
 echo PASS
 echo
 
 # 4. Requant mode without '--keep-split'
-$QUANTIZE --allow-requantize $WORK_PATH/ggml-model-split-00001-of-00006.gguf $WORK_PATH/ggml-model-requant-merge.gguf Q4_K
+$QUANTIZE --allow-requantize $WORK_PATH/ggml-model-split-00001-of-00012.gguf $WORK_PATH/ggml-model-requant-merge.gguf Q4_K
 echo PASS
 echo
 
 # 4b. Test the requanted model is loading properly
-$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-merge.gguf --n-predict 32
+$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-merge.gguf -p "I believe the meaning of life is" --n-predict 32
 echo PASS
 echo