# QNN Gen AI Transformer

## Model download

Download bge-large-en-v1.5 from [https://huggingface.co/BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5)

## Model conversion

The following section demonstrates converting a model using
[qnn-genai-transformer-composer](https://docs.qualcomm.com/doc/80-63442-10/topic/qnn-genai-transformer-composer.html#qnn-genai-transformer-composer).

**Model conversion on Linux and Android**

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 --outfile <output filename with complete path>.bin
                                     --model <path-to-downloaded-BGE-model-directory>
    Copy to clipboard

## Model configuration

See [Genie Embedding JSON configuration string](https://docs.qualcomm.com/doc/80-63442-10/topic/embedding_json.html#genie-embedding-json-config-string) for details on the fields and what
they mean. An example model config can be found at
`${QNN_SDK_ROOT}/examples/Genie/configs/bge-large-genaitransformer.json`. Note that the tokenizer path and
model bin fields will need to be updated based on your actual preparation steps.

## Model execution

The following section demonstrates running a model on the QNN GenAITransformer backend using
[genie-t2e-run](https://docs.qualcomm.com/doc/80-63442-10/topic/genie-t2t-run.html#genie-t2e-run).

Note

Results will be saved in output.raw file in the working directory.

**Model execution on Linux**

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
    ./genie-t2e-run -c <path to bge-large-genaitransformer.json>
                    -p "Tell me about Qualcomm"
    Copy to clipboard

**Model execution on Android**

Open a command shell on Linux host and run:

# make sure a test device is connected
    adb devices
    
    # push artifacts to device
    adb push ${QNN_SDK_ROOT}/bin/aarch64-android/genie-t2e-run /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 <path to tokenizer.json> /data/local/tmp/
    adb push <path to bge-large-genaitransformer.json> /data/local/tmp/
    adb push <path to model bin file, e.g. <path-to-downloaded-BGE-model-directory>/model.bin> /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-t2e-run -c <path to bge-large-genaitransformer.json>
                    -p "Tell me about Qualcomm"
    Copy to clipboard

Last Published: Aug 06, 2026

[Previous Topic
QNN HTP](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/bge-large_htp_htp.md) [Next Topic
Genie Engine](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/engine_engine.md)