how is this:

    npx dalai llama 7B
    npx dalai serve

    # build this repo
    git clone https://github.com/ggerganov/llama.cpp
    cd llama.cpp
    make

    #For Windows and CMake, use the following command instead:
    cd <path_to_llama_folder>
    mkdir build
    cd build
    cmake ..
    cmake --build . --config Release

    # obtain the original LLaMA model weights and place them in ./models
    ls ./models
    65B 30B 13B 7B tokenizer_checklist.chk tokenizer.model

    # install Python dependencies
    python3 -m pip install torch numpy sentencepiece

    # convert the 7B model to ggml FP16 format
    python3 convert-pth-to-ggml.py models/7B/ 1

    # quantize the model to 4-bits (using method 2 = q4_0)
    ./quantize ./models/7B/ggml-model-f16.bin ./models/7B/ggml-model-q4_0.bin 2

    # run the inference
    ./main -m ./models/7B/ggml-model-q4_0.bin -n 128