public class Example {

	public static void main(String... args) throws IOException {
        LlamaModel.setLogger((level, message) -> System.out.print(message));
        ModelParameters modelParams = new ModelParameters()
                .setNGpuLayers(43);
        InferenceParameters inferParams = new InferenceParameters()
                .setTemperature(0.7f)
                .setPenalizeNl(true)
                .setMirostat(InferenceParameters.MiroStat.V2)
                .setAntiPrompt("\n");

        String modelPath = "/run/media/konstantin/Seagate/models/llama2/llama-2-13b-chat/ggml-model-q4_0.gguf";
        String system = "This is a conversation between User and Llama, a friendly chatbot.\n" +
                "Llama is helpful, kind, honest, good at writing, and never fails to answer any " +
                "requests immediately and with precision.\n";
        BufferedReader reader = new BufferedReader(new InputStreamReader(System.in, StandardCharsets.UTF_8));
        try (LlamaModel model = new LlamaModel(modelPath, modelParams)) {
            System.out.print(system);
            String prompt = system;
            while (true) {
                prompt += "\nUser: ";
                System.out.print("\nUser: ");
                String input = reader.readLine();
                prompt += input;
                System.out.print("Llama: ");
                prompt += "\nLlama: ";
                for (String output : model.generate(prompt, inferParams)) {
                    System.out.print(output);
                    prompt += output;
                }
            }
        }
    }
}

try (LlamaModel model = new LlamaModel("/path/to/gguf-model")) {
    // Stream a response and access more information about each output.
    for (String output : model.generate("Tell me a joke.")) {
        System.out.print(output);
    }
    // Calculate a whole response before returning it.
    String response = model.complete("Tell me another one");
    // Returns the hidden representation of the context + prompt.
    float[] embedding = model.embed("Embed this");
}

ModelParameters modelParams = new ModelParameters()
                            .setLoraAdapter("/path/to/lora/adapter")
                            .setLoraBase("/path/to/lora/base");
InferenceParameters inferParams = new InferenceParameters()
		.setGrammar(new File("/path/to/grammar.gbnf"))
        .setTemperature(0.8);
LlamaModel model = new LlamaModel("/path/to/model.bin", modelParams);
model.generate(prompt, inferParams)

// The method accepts a BiConsumer<LogLevel, String>.
LlamaModel.setLogger((level, message) -> System.out.println(level.name() + ": " + message));
// To completely silence any output, pass a no-op.
LlamaModel.setLogger((level, message) -> {});

// Similarly, a progress callback can be set (only the C++ side will call this).
// I think this is only used to report progress loading the model with a value of 0-1.
// It is thus state specific and can be done via the parameters.
new ModelParameters()
        .setProgressCallback(progress -> System.out.println("progress: " + progress));