model_config.json

{
    "quantization": "INT4",
    "compute_units": "cpuAndGPU",
    "hidden_size": 2048,
    "vocab_size": 65536,
    "max_seq_len": 512,
    "architecture": "lfm25",
    "layer_types": [
        "conv",
        "conv",
        "full_attention",
        "conv",
        "conv",
        "full_attention",
        "conv",
        "conv",
        "full_attention",
        "conv",
        "full_attention",
        "conv",
        "full_attention",
        "conv",
        "full_attention",
        "conv"
    ]
}