config.json

{
    "architectures": [
        "DFlashDraftModel"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoModel": "dflash.DFlashDraftModel"
    },
    "block_size": 16,
    "dflash_config": {
        "mask_token_id": 248070,
        "target_layer_ids": [
            1,
            8,
            15,
            22,
            29
        ]
    },
    "dtype": "bfloat16",
    "eos_token_id": 248044,
    "head_dim": 128,
    "hidden_act": "silu",
    "hidden_size": 2560,
    "initializer_range": 0.02,
    "intermediate_size": 9728,
    "layer_types": [
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention",
        "full_attention"
    ],
    "max_position_embeddings": 262144,
    "max_window_layers": 5,
    "model_type": "qwen3",
    "num_attention_heads": 32,
    "num_hidden_layers": 5,
    "num_key_value_heads": 8,
    "num_target_layers": 32,
    "pad_token_id": 248044,
    "quantization": {
        "group_size": 64,
        "bits": 6,
        "mode": "affine"
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 6,
        "mode": "affine"
    },
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 10000000,
    "sliding_window": null,
    "tie_word_embeddings": true,
    "transformers_version": "4.57.1",
    "use_cache": true,
    "use_sliding_window": false,
    "vision_config": {},
    "vocab_size": 248320
}