{ "architectures": [ "LoopedGDNForCausalLM" ], "model_type": "looped_gdn", "auto_map": { "AutoConfig": "configuration_looped_gdn.LoopedGDNConfig", "AutoModelForCausalLM": "modeling_looped_gdn.LoopedGDNForCausalLM" }, "qwen_config": { "transformers_version": "5.18.0", "architectures": null, "output_hidden_states": false, "return_dict": true, "dtype": "bfloat16", "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "problem_type": null, "vocab_size": 248320, "hidden_size": 2048, "intermediate_size": 6144, "num_hidden_layers": 24, "num_attention_heads": 8, "num_key_value_heads": 2, "hidden_act": "silu", "max_position_embeddings": 262144, "initializer_range": 0.02, "rms_norm_eps": 1e-06, "use_cache": true, "tie_word_embeddings": true, "rope_parameters": { "mrope_interleaved": true, "mrope_section": [ 11, 11, 10 ], "rope_type": "default", "rope_theta": 10000000, "partial_rotary_factor": 0.25 }, "attention_bias": false, "attention_dropout": 0.0, "head_dim": 256, "linear_conv_kernel_dim": 4, "linear_key_head_dim": 128, "linear_value_head_dim": 128, "linear_num_key_heads": 16, "linear_num_value_heads": 16, "layer_types": [ "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention", "linear_attention" ], "pad_token_id": null, "bos_token_id": null, "eos_token_id": 248044, "_name_or_path": "", "attn_output_gate": true, "full_attention_interval": 4, "mlp_only_layers": [], "model_type": "qwen3_5_text", "mtp_num_hidden_layers": 1, "mtp_use_dedicated_embeddings": false, "mamba_ssm_dtype": "float32", "partial_rotary_factor": 0.25, "output_attentions": false }, "num_groups": 6, "loops_per_group": 4, "halt_threshold": null, "gate_init_bias": 4.0, "lora_rank": 128, "loops": [ 4, 4, 4, 4, 4, 4 ], "hidden_size": 2048, "vocab_size": 248320, "num_hidden_layers": 24, "tie_word_embeddings": true, "eos_token_id": 248044, "dtype": "bfloat16" }