{ "attention_bias": false, "attention_dropout": 0.0, "attn_output_gate": true, "bos_token_id": 248044, "dtype": "bfloat16", "eos_token_id": 248044, "full_attention_interval": 4, "head_dim": 256, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "layer_types": [ "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention" ], "linear_conv_kernel_dim": 4, "linear_key_head_dim": 128, "linear_num_key_heads": 16, "linear_num_value_heads": 32, "linear_value_head_dim": 128, "mamba_ssm_dtype": "float32", "max_position_embeddings": 262144, "model_type": "qwen4_exp_text", "moe_intermediate_size": 512, "mtp_num_hidden_layers": 1, "mtp_use_dedicated_embeddings": false, "num_attention_heads": 16, "num_experts": 180, "num_experts_per_tok": 8, "num_hidden_layers": 40, "num_key_value_heads": 2, "output_router_logits": false, "pad_token_id": null, "partial_rotary_factor": 0.25, "rms_norm_eps": 1e-06, "rope_parameters": { "mrope_interleaved": true, "mrope_section": [ 11, 11, 10 ], "partial_rotary_factor": 0.25, "rope_theta": 10000000, "rope_type": "default" }, "router_aux_loss_coef": 0.001, "shared_expert_intermediate_size": 512, "tie_word_embeddings": false, "use_cache": true, "vocab_size": 248320, "architectures": [ "Qwen4ExpForCausalLM" ], "transformers_version": "4.57.1", "hc_count": 4, "hc_lowrank": 320, "indexer_n_heads": 4, "indexer_head_dim": 128, "indexer_budget": 262144, "indexer_compress_ratio": 4, "indexer_kv_heads": 1, "output_gate_type": "sigmoid", "ple_layer_ids": [ 2 ], "ngram_size": 3, "heads_per_ngram": 4, "ple_conv_kernel_size": 4, "split_ngram_parts": 5, "ple_embed_dim": 2048, "num_embeddings_per_layer_input": 256, "make_ngram_vocab_size_divisible_by": 128, "ngram_vocab_size_base": 4880000 }