{ "architectures": [ "DFlash2DraftModel" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": null, "is_causal": false, "dflash_config": { "block_size": 8, "conv_group_size": 16, "conv_kernel_size": 2, "mask_token_id": 248070, "selector_rank": 256, "selector_top_k": 16, "target_layer_ids": [ 5, 19, 33, 47, 61 ] }, "dtype": "bfloat16", "eos_token_id": 248044, "head_dim": 128, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 17408, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_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": 64, "pad_token_id": 248044, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 10000000, "rope_type": "default" }, "sliding_window": 2048, "tie_word_embeddings": false, "transformers_version": "5.15.0", "use_cache": true, "use_sliding_window": true, "vocab_size": 248320, "quantization_config": { "quant_method": "compressed-tensors", "config_groups": { "group_0": { "format": "pack-quantized", "input_activations": null, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 128, "num_bits": 8, "observer": "memoryless_minmax", "observer_kwargs": {}, "scale_dtype": null, "strategy": "group", "symmetric": true, "type": "int", "zp_dtype": null } } }, "format": "pack-quantized", "global_compression_ratio": null, "ignore": [ "candidate_selector", "re:.*_conv.*" ] } }