| { |
| "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": 393216, |
| "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": { |
| "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": 4, |
| "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": [ |
| "re:.*kernel_projection$", |
| "re:.*candidate_selector.*", |
| "re:.*hidden_projection$" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.17.0" |
| } |
| } |
