Function load_models 

pub(super) fn load_models(
    cache_dir: &Path,
    show_download_progress: bool,
    model_variant: ModelVariant,
    max_seq_length: usize,
    intra_threads: usize,
) -> Result<(Session, Tokenizer)>

Downloads (if not already cached) and loads both the ORT session and the tokenizer for the given model variant, returning them as a pair.