# Genie Pipeline

This section contains tutorials that pertain to running wt19-en-de on GenAiTransformer using GeniePipeline and GenieNode APIs.
The API invocations are constructed using genie-app tool.

## GenAiTransformer Backend Example

See [Genie Node JSON configuration string](https://docs.qualcomm.com/doc/80-63442-100/topic/node_json.html##genie-node-json-config-string) for details on the fields and what
they mean. Example model\_configs and script to tie together Node and Pipeline calls can be found at
`${QNN_SDK_ROOT}/examples/Genie/configs/wt19-en-de/`.

**Model Download**

Download the model from: [https://huggingface.co/facebook/wmt19-en-de](https://huggingface.co/facebook/wmt19-en-de)

**Model Preparation**

Open a command shell on Linux host and run:

# Make sure environment is setup as per instructions, or can cd into bin folder on Linux host
    cd ${QNN_SDK_ROOT}/bin/x86_64-linux-clang/
    ./qnn-genai-transformer-composer --model <path to model> --outfile <output filename with complete path> --export_tokenizer_json --dump_lut
    Copy to clipboard

Eg:

qnn-genai-transformer-composer --model wt19_en_de_model --outfile wt19_en_de_model_artifacts/model.bin --export_tokenizer_json --dump_lut
    Copy to clipboard

This will generate model\_encoder.bin, model\_decoder.bin, LUT.bin and tokenizer.json inside wt19\_en\_de\_model\_artifacts.

**Model Inference on Android**

To run on QNN GenAiTransformer backend, open a command shell on android and run the following.

adb shell mkdir -p /data/local/tmp/
    adb push ${QNN_SDK_ROOT}/bin/aarch64-android/genie-app /data/local/tmp/
    adb push ${QNN_SDK_ROOT}/lib/aarch64-android/libGenie.so /data/local/tmp/
    adb push ${QNN_SDK_ROOT}/lib/aarch64-android/libQnnGenAiTransformer.so /data/local/tmp/
    adb push ${QNN_SDK_ROOT}/lib/aarch64-android/libQnnGenAiTransformerModel.so /data/local/tmp/
    adb push ${QNN_SDK_ROOT}/lib/aarch64-android/libQnnGenAiTransformerCpuOpPkg.so /data/local/tmp/
    adb push <path to text-encoder.json> /data/local/tmp/
    adb push <path to text-generator.json> /data/local/tmp/
    adb push <path to LUT.bin> /data/local/tmp/
    adb push <path to tokenizer.json> /data/local/tmp/
    adb push <path to model bin files> /data/local/tmp/
    adb push <path to LMMScript> /data/local/tmp/
    
    # open adb shell
    adb shell
    
    export LD_LIBRARY_PATH=/data/local/tmp/
    export PATH=$LD_LIBRARY_PATH:$PATH
    
    cd $LD_LIBRARY_PATH
    ./genie-app -s <path to LMMScript>
    Copy to clipboard

Last Published: Oct 02, 2025

[Previous Topic
HTP Backend Example Model Config and Backend Extension Config](https://docs.qualcomm.com/bundle/publicresource/80-63442-100/topics/glm-4v.md) [Next Topic
Library](https://docs.qualcomm.com/bundle/publicresource/80-63442-100/topics/library.md)