{ "architectures": [ "DFlashDraftModel" ], "auto_map": { "": "config.DFlashSpeculatorConfig" }, "aux_hidden_state_layer_ids": [ 3, 13, 23, 32, 42 ], "block_size": 8, "draft_vocab_size": 32000, "dtype": "bfloat16", "mask_token_id": 1, "max_anchors": 3072, "sliding_window_non_causal": false, "speculators_config": { "algorithm": "dflash", "default_proposal_method": "greedy", "proposal_methods": [ { "accept_tolerance": 0.0, "proposal_type": "greedy", "speculative_tokens": 7, "verifier_accept_k": 1 } ], "verifier": { "architectures": [], "name_or_path": "deepseek-ai/DeepSeek-V4-Flash" } }, "speculators_model_type": "dflash", "speculators_version": "0.5.0.dev163", "target_hidden_size": null, "tie_word_embeddings": false, "transformer_layer_config": { "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hc_mult": 4, "head_dim": 256, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 2048, "layer_types": [ "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention", "sliding_attention" ], "max_position_embeddings": 1048576, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 64, "num_hidden_layers": 5, "num_key_value_heads": 1, "pad_token_id": null, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 10000, "rope_type": "default" }, "sliding_window": 2048, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 129280 }, "transformers_version": "5.10.2" }