# Preparation (LoRA) Note This section demonstrates LLaMA-2-7b model workflow with LoRA adapter via `genie-t2t-run`. ## Adapter Download Download Llama-2-7b lora adapter (French to English language translator) from [https://huggingface.co/kaitchup/Llama-2-7b-mt-French-to-English](https://huggingface.co/kaitchup/Llama-2-7b-mt-French-to-English). ## Preparation The following section demonstrates converting a LoRA adapter using [qnn-genai-transformer-composer](https://docs.qualcomm.com/doc/80-63442-10/topic/qnn-genai-transformer-composer.html#qnn-genai-transformer-composer). 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 # Additionally do the following export LD_LIBRARY_PATH=${QNN_SDK_ROOT}/lib/x86_64-linux-clang:$LD_LIBRARY_PATH export PYTHONPATH=${QNN_SDK_ROOT}/lib/python/qti/aisw/genai:$PYTHONPATH # LoRA adapter conversion command cd ${QNN_SDK_ROOT}/bin/x86_64-linux-clang/ ./qnn-genai-transformer-composer --model --outfile .bin --lora Copy to clipboard ## Dialog JSON Configuration See [Genie Dialog JSON configuration string](https://docs.qualcomm.com/doc/80-63442-10/topic/dialog_json.html#genie-dialog-json-config-string) for details on the fields and what they mean. An example model config can be found at `${QNN_SDK_ROOT}/examples/Genie/configs/llama2-7b/llama2-7b-genaitransformer-lora.json`. Note that the tokenizer path and model bin fields will need to be updated based on your actual preparation steps. ## Inference Choose your target platform for inference: - [Linux](https://docs.qualcomm.com/doc/80-63442-10/topic/linux_inference.html) - [Android](https://docs.qualcomm.com/doc/80-63442-10/topic/android_inference.html) Last Published: Aug 06, 2026 [Previous Topic Linux](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/linux.md) [Next Topic Linux](https://docs.qualcomm.com/bundle/publicresource/80-63442-10/topics/linux_inference.md)