| { | |
| "architectures": [ | |
| "DFlashDraftModel" | |
| ], | |
| "model_type": "qwen3", | |
| "hidden_size": 4096, | |
| "intermediate_size": 11008, | |
| "num_hidden_layers": 8, | |
| "num_attention_heads": 32, | |
| "num_key_value_heads": 8, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "rms_norm_eps": 1e-06, | |
| "attention_bias": false, | |
| "vocab_size": 129280, | |
| "max_position_embeddings": 65536, | |
| "rope_theta": 500000, | |
| "rope_scaling": null, | |
| "sliding_window": 128, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention" | |
| ], | |
| "block_size": 11, | |
| "num_target_layers": 32, | |
| "torch_dtype": "bfloat16", | |
| "tie_word_embeddings": false, | |
| "dflash_config": { | |
| "mask_token_id": 128000, | |
| "target_layer_ids": [ | |
| 1, | |
| 5, | |
| 9, | |
| 13, | |
| 17, | |
| 21, | |
| 25, | |
| 29 | |
| ], | |
| "num_target_layers": 32, | |
| "block_size": 11, | |
| "use_attention_sink": true, | |
| "sliding_window": 128 | |
| } | |
| } |