Finalize releases/2023/3 (openvinotoolkit#182)

Author: Wovchena

.github/workflows/causal_lm_cpp.yml

@@ -23,7 +23,7 @@ jobs:
       - name: Install OpenVINO
         run: |
           mkdir ./ov/
-          curl https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.0.0-14004-a240ae8fadd/l_openvino_toolkit_ubuntu20_2024.0.0.dev20240116_x86_64.tgz | tar --directory ./ov/ --strip-components 1 -xz
+          curl https://storage.openvinotoolkit.org/repositories/openvino/packages/2023.3/linux/l_openvino_toolkit_ubuntu20_2023.3.0.13775.ceeafaf64f3_x86_64.tgz | tar --directory ./ov/ --strip-components 1 -xz
           sudo ./ov/install_dependencies/install_openvino_dependencies.sh
       - name: Download, convert and build
         run: |
@@ -49,7 +49,7 @@ jobs:
       - name: Install OpenVINO
         run: |
           mkdir ./ov/
-          curl https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.0.0-14004-a240ae8fadd/l_openvino_toolkit_ubuntu20_2024.0.0.dev20240116_x86_64.tgz | tar --directory ./ov/ --strip-components 1 -xz
+          curl https://storage.openvinotoolkit.org/repositories/openvino/packages/2023.3/linux/l_openvino_toolkit_ubuntu20_2023.3.0.13775.ceeafaf64f3_x86_64.tgz | tar --directory ./ov/ --strip-components 1 -xz
           sudo ./ov/install_dependencies/install_openvino_dependencies.sh
       - name: Download, convert and build
         run: |
@@ -138,20 +138,20 @@ jobs:
       - name: Install OpenVINO
         shell: bash
         run: |
-          curl --output ov.zip https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.0.0-14004-a240ae8fadd/w_openvino_toolkit_windows_2024.0.0.dev20240116_x86_64.zip
+          curl --output ov.zip https://storage.openvinotoolkit.org/repositories/openvino/packages/2023.3/windows/w_openvino_toolkit_windows_2023.3.0.13775.ceeafaf64f3_x86_64.zip
           unzip ov.zip
       - name: Download, convert and build
         shell: cmd
         run: |
-          call w_openvino_toolkit_windows_2024.0.0.dev20240116_x86_64\setupvars.bat
+          call w_openvino_toolkit_windows_2023.3.0.13775.ceeafaf64f3_x86_64\setupvars.bat
           python -m pip install --upgrade-strategy eager transformers==4.35.2 "optimum>=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 TinyLlama/TinyLlama-1.1B-Chat-v1.0 --output_dir ./TinyLlama-1.1B-Chat-v1.0/ --precision FP16 --stateful
           cmake -DCMAKE_BUILD_TYPE=Release -S ./text_generation/causal_lm/cpp/ -B ./build/
           cmake --build ./build/ --config Release -j
       - name: Compare
         shell: cmd
         run: |
-          call w_openvino_toolkit_windows_2024.0.0.dev20240116_x86_64\setupvars.bat
+          call w_openvino_toolkit_windows_2023.3.0.13775.ceeafaf64f3_x86_64\setupvars.bat
           convert_tokenizer .\TinyLlama-1.1B-Chat-v1.0\pytorch\dldt\FP16\ --output .\TinyLlama-1.1B-Chat-v1.0\pytorch\dldt\FP16\ --with-detokenizer
 
           .\build\Release\beam_search_causal_lm.exe .\TinyLlama-1.1B-Chat-v1.0\pytorch\dldt\FP16\ "69" > .\pred.txt
@@ -178,7 +178,7 @@ jobs:
       - name: Install OpenVINO
         run: |
           mkdir ./ov/
-          curl https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.0.0-14004-a240ae8fadd/l_openvino_toolkit_ubuntu20_2024.0.0.dev20240116_x86_64.tgz | tar --directory ./ov/ --strip-components 1 -xz
+          curl https://storage.openvinotoolkit.org/repositories/openvino/packages/2023.3/linux/l_openvino_toolkit_ubuntu20_2023.3.0.13775.ceeafaf64f3_x86_64.tgz | tar --directory ./ov/ --strip-components 1 -xz
           sudo ./ov/install_dependencies/install_openvino_dependencies.sh
       - name: Download, convert and build
         run: |

.github/workflows/stable_diffusion_1_5_cpp.yml

@@ -23,7 +23,7 @@ jobs:
         run: |
           set -e
           mkdir openvino
-          curl https://storage.openvinotoolkit.org/repositories/openvino/packages/nightly/2024.0.0-14004-a240ae8fadd/l_openvino_toolkit_ubuntu20_2024.0.0.dev20240116_x86_64.tgz | tar --directory ./openvino/ --strip-components 1 -xz
+          curl https://storage.openvinotoolkit.org/repositories/openvino/packages/2023.3/linux/l_openvino_toolkit_ubuntu20_2023.3.0.13775.ceeafaf64f3_x86_64.tgz | tar --directory ./openvino/ --strip-components 1 -xz
           sudo ./openvino/install_dependencies/install_openvino_dependencies.sh
           sudo apt install libeigen3-dev
       - name: Download / convert models

README.md

@@ -9,9 +9,6 @@ It includes the following pipelines:
 2. [Text generation C++ samples that support most popular models like LLaMA 2](./text_generation/causal_lm/cpp/)
 3. [Stable Diffuison (with LoRA) C++ image generation pipeline](./image_generation/stable_diffusion_1_5/cpp/)
 
-> [!NOTE]
-> This project is not for production use.
-
 ### License
 
 The GenAI repository is licensed under [Apache License Version 2.0](LICENSE).
@@ -22,6 +19,6 @@ your contribution under these terms.
 
 Requirements may vary for different samples. See respective readme files for more details,
 and make sure to install the OpenVINO version listed there. Refer to documentation to see
-[how to install OpenVINO](docs.openvino.ai/install).
+[how to install OpenVINO](https://docs.openvino.ai/install).
 
 The supported devices are CPU and GPU including Intel discrete GPU.

image_generation/stable_diffusion_1_5/cpp/README.md

@@ -8,7 +8,7 @@ The pure C++ text-to-image pipeline, driven by the OpenVINO native C++ API for S
 
 C++ Packages:
 * [CMake](https://cmake.org/download/): Cross-platform build tool
-* [OpenVINO](docs.openvino.ai/install): Model inference
+* [OpenVINO](https://docs.openvino.ai/install): Model inference
 * [Eigen3](https://anaconda.org/conda-forge/eigen): LoRA enabling
 
 Prepare a python environment and install dependencies:

llm_bench/python/README.md

@@ -69,7 +69,7 @@ pip install -r requirements.txt
 note: **You can specify the installed openvino version through pip install**
 ``` bash
 # e.g. 
-pip install openvino==2023.2.0
+pip install openvino==2023.3.0
 ```
 
 ### 4. Run the following command to test the performance of one LLM model
@@ -120,4 +120,4 @@ python ./benchmark.py -m models/llama-2-7b-chat/pytorch -d CPU --torch_compile_b
 ### 1. NOTE
 > If you encounter any errors, please check **[NOTES.md](./doc/NOTES.md)** which provides solutions to the known errors.
 ### 2. Image generation
-> If you need to set parameters for image generation, you need to prepare a prompt file, please check **[IMAGE_GEN.md](./doc/IMAGE_GEN.md)**
+> If you need to set parameters for image generation, you need to prepare a prompt file, please check **[IMAGE_GEN.md](./doc/IMAGE_GEN.md)**

text_generation/causal_lm/cpp/README.md

@@ -2,9 +2,6 @@
 
 These examples showcase inference of text-generation Large Language Models (LLMs): `chatglm`, `LLaMA`, `Qwen` and other models with the same signature. The applications don't have many configuration options to encourage the reader to explore and modify the source code. Loading `user_ov_extensions` provided by `openvino-tokenizers` to `ov::Core` enables tokenization. Run `convert_tokenizer` to generate IRs for the samples. [group_beam_searcher.hpp](group_beam_searcher.hpp) implements the algorithm of the same name, which is used by `beam_search_causal_lm`. There is also a Jupyter [notebook](https://github.com/openvinotoolkit/openvino_notebooks/tree/main/notebooks/254-llm-chatbot) which provides an example of LLM-powered Chatbot in Python.
 
-> [!NOTE]
-> This project is not for production use.
-
 ## How it works
 
 ### greedy_causal_lm
@@ -15,9 +12,9 @@ The program loads a tokenizer, a detokenizer and a model (`.xml` and `.bin`) to
 
 The program loads a tokenizer, a detokenizer and a model (`.xml` and `.bin`) to OpenVINO. A prompt is tokenized and passed to the model. The model predicts a distribution over the next tokens and group beam search samples from that distribution to explore possible sequesnses. The result is converted to chars and printed.
 
-## Install OpenVINO Runtime
+## Install OpenVINO
 
-Install OpenVINO Runtime from an archive: [Linux](https://docs.openvino.ai/2023.2/openvino_docs_install_guides_installing_openvino_from_archive_linux.html). `<INSTALL_DIR>` below refers to the extraction location.
+Install [OpenVINO Archives >= 2023.3](https://docs.openvino.ai/install). `<INSTALL_DIR>` below refers to the extraction location.
 
 ## Build `greedy_causal_lm`, `beam_search_causal_lm` and `user_ov_extensions`