| { | |
| "architectures": [ | |
| "DFlashDraftModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "block_size": 8, | |
| "dtype": "bfloat16", | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 12288, | |
| "layer_types": [ | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "mask_token_id": 155697, | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 2, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 2, | |
| "num_key_value_heads": 8, | |
| "num_target_layers": 36, | |
| "resolution_scale": 1.0, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "target_layer_ids": [ | |
| 24, | |
| 30, | |
| 31, | |
| 32, | |
| 34 | |
| ], | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.1", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 155697 | |
| } | |