Add --save_orig

Author: Wovchena

text_generation/causal_lm/cpp/README.md

@@ -47,7 +47,7 @@ The `--upgrade-strategy eager` option is needed to ensure `optimum-intel` is upg
 ```sh
 source <INSTALL_DIR>/setupvars.sh
 python -m pip install --upgrade-strategy eager "optimum[openvino]>=1.14" -r ../../../llm_bench/python/requirements.txt ../../../thirdparty/openvino_contrib/modules/custom_operations/[transformers] --extra-index-url https://download.pytorch.org/whl/cpu
-python ../../../llm_bench/python/convert.py --model_id meta-llama/Llama-2-7b-hf --output_dir ./Llama-2-7b-hf/ --stateful
+python ../../../llm_bench/python/convert.py --model_id meta-llama/Llama-2-7b-hf --output_dir ./Llama-2-7b-hf/ --save_orig --stateful
 python ./convert_tokenizers.py ./Llama-2-7b-hf/
 ```
 

text_generation/causal_lm/cpp/set_up_and_run.sh

@@ -17,7 +17,7 @@ curl https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/
 sudo ./ov/install_dependencies/install_openvino_dependencies.sh
 
 source ./ov/setupvars.sh
-python -m pip install --upgrade-strategy eager "optimum[openvino]>=1.14" -r ../../../llm_bench/python/requirements.txt ../../../thirdparty/openvino_contrib/modules/custom_operations/[transformers] --extra-index-url https://download.pytorch.org/whl/cpu && python ../../../llm_bench/python/convert.py --model_id openlm-research/open_llama_3b_v2 --output_dir ./open_llama_3b_v2/ --stateful &
+python -m pip install --upgrade-strategy eager "optimum[openvino]>=1.14" -r ../../../llm_bench/python/requirements.txt ../../../thirdparty/openvino_contrib/modules/custom_operations/[transformers] --extra-index-url https://download.pytorch.org/whl/cpu && python ../../../llm_bench/python/convert.py --model_id openlm-research/open_llama_3b_v2 --output_dir ./open_llama_3b_v2/ --save_orig --stateful &
 cmake -DCMAKE_BUILD_TYPE=Release -S ./ -B ./build/
 cmake --build ./build/ --config Release -j
 wait