{ "_name_or_path": "", "architectures": [ "DFlash2DraftModel" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": null, "chunk_size_feed_forward": 0, "deepspec_dflash2": { "dpace_alpha": 0.5, "flatten_frozen_head": true, "kl_decay": 1.0, "kl_scale": 1.0, "lk_loss_type": "lambda", "loss_decay_gamma": 7.0, "loss_type": "dpace", "num_anchors": 128, "objective_checkpoint": false, "objective_chunk_blocks": 32, "prediction_only_head": true, "selector_loss_alpha": 1.0, "selector_stop_gradient": false, "version": 1 }, "dflash_config": { "block_size": 12, "conv_group_size": 16, "conv_kernel_size": 2, "mask_token_id": 154821, "selector_rank": 256, "selector_top_k": 16, "target_layer_ids": [ 1, 20, 38, 56, 75 ] }, "dspark_loss_profile": "legacy", "dtype": "bfloat16", "eos_token_id": [ 154820, 154827, 154829 ], "head_dim": 128, "hidden_act": "silu", "hidden_size": 6144, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 12288, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "full_attention" ], "max_position_embeddings": 1048576, "max_window_layers": 28, "model_type": "qwen3", "num_attention_heads": 64, "num_hidden_layers": 5, "num_key_value_heads": 16, "num_target_layers": 78, "output_attentions": false, "output_hidden_states": false, "pad_token_id": 154820, "problem_type": null, "return_dict": true, "rms_norm_eps": 1e-05, "rope_parameters": { "rope_theta": 8000000.0, "rope_type": "default" }, "sliding_window": 2048, "tie_word_embeddings": false, "transformers_version": "5.17.0", "use_cache": false, "use_sliding_window": true, "vocab_size": 154880 }