ci : use -no-cnv in gguf-split tests (ggml-org#11254)

* ci : use -no-cnv in gguf-split tests

ggml-ci

* ci : use -no-cnv in requantize tests

ggml-ci

* scripts : fix [no ci]

Author: ggerganov

examples/gguf-split/tests.sh

@@ -41,7 +41,7 @@ echo PASS
 echo
 
 # 2b. Test the sharded model is loading properly
-$MAIN --model $WORK_PATH/ggml-model-split-00001-of-00006.gguf --n-predict 32
+$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-00001-of-00006.gguf --n-predict 32
 echo PASS
 echo
 
@@ -51,7 +51,7 @@ echo PASS
 echo
 
 # 3b. Test the merged model is loading properly
-$MAIN --model $WORK_PATH/ggml-model-merge.gguf --n-predict 32
+$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge.gguf --n-predict 32
 echo PASS
 echo
 
@@ -61,7 +61,7 @@ echo PASS
 echo
 
 # 4b. Test the sharded model is loading properly
-$MAIN --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-00007.gguf --n-predict 32
 echo PASS
 echo
 
@@ -71,7 +71,7 @@ echo
 #echo
 
 # 5b. Test the merged model is loading properly
-#$MAIN --model $WORK_PATH/ggml-model-merge-2.gguf --n-predict 32
+#$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge-2.gguf --n-predict 32
 #echo PASS
 #echo
 
@@ -81,7 +81,7 @@ echo PASS
 echo
 
 # 6b. Test the sharded model is loading properly
-$MAIN --model $WORK_PATH/ggml-model-split-2G-00001-of-00002.gguf --n-predict 32
+$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-2G-00001-of-00002.gguf --n-predict 32
 echo PASS
 echo
 

examples/quantize/tests.sh

@@ -47,7 +47,7 @@ echo PASS
 echo
 
 # 3a. Test the requanted model is loading properly
-$MAIN --model $WORK_PATH/ggml-model-requant-00001-of-00006.gguf --n-predict 32
+$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-00001-of-00006.gguf --n-predict 32
 echo PASS
 echo
 
@@ -57,7 +57,7 @@ echo PASS
 echo
 
 # 4b. Test the requanted model is loading properly
-$MAIN --model $WORK_PATH/ggml-model-requant-merge.gguf --n-predict 32
+$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-merge.gguf --n-predict 32
 echo PASS
 echo
 

scripts/hf.sh

@@ -80,18 +80,18 @@ run_conversion_and_inference_lora() {
     # Run inference
     echo -e "\n\n---------------------------\n\n"
     echo "Running llama-cli without lora for $model_name with hidden_size $hidden_size..."
-    OUTPUT_BASE=$(./llama-cli -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
+    OUTPUT_BASE=$(./llama-cli -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
         -p "$EXPECTED_BASE_FIRST_WORD" -n 50 --seed 42 --temp 0)
 
     echo -e "\n\n---------------------------\n\n"
     echo "Running llama-cli with hot lora for $model_name with hidden_size $hidden_size..."
-    OUTPUT_LORA_HOT=$(./llama-cli -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
+    OUTPUT_LORA_HOT=$(./llama-cli -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32.gguf \
         --lora $MODELS_REPO/$model_name/hidden_size=$hidden_size/lora/Lora-F32-LoRA.gguf \
         -p "$EXPECTED_LORA_FIRST_WORD" -n 50 --seed 42 --temp 0)
 
     echo -e "\n\n---------------------------\n\n"
     echo "Running llama-cli with merged lora for $model_name with hidden_size $hidden_size..."
-    OUTPUT_LORA_MERGED=$(./llama-cli -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32-lora-merged.gguf \
+    OUTPUT_LORA_MERGED=$(./llama-cli -no-cnv -m $MODELS_REPO/$model_name/hidden_size=$hidden_size/base/Base-F32-lora-merged.gguf \
         -p "$EXPECTED_LORA_FIRST_WORD" -n 50 --seed 42 --temp 0)
 
     # Remove any initial white space