{ "model_type": "memt_qwen3_5_moe", "pad_token_id": 248044, "architectures": [ "MemTQwen3_5MoeForCausalLM" ], "torch_dtype": "bfloat16", "tie_word_embeddings": false, "backbone_configs": { "model_type": "qwen3_5_moe", "text_config": { "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": "qwen3_5_moe_text", "moe_intermediate_size": 512, "mtp_num_hidden_layers": 1, "mtp_use_dedicated_embeddings": false, "num_attention_heads": 16, "num_experts": 256, "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 } }, "memt": { "memory_update_mode": "token", "gdn_version": "stable_gdn2", "memory_use_short_conv": false, "memory_head_mode": "mha", "memory_read_scale": "k_inv_sqrt", "num_memory_heads": 16, "num_kv_heads": 16, "linear_attention_state_policy": "reset_per_chunk", "chunk_tokens": 2048, "tail_policy": "commit", "output_gate_type": "silu", "output_gate_bias": false, "output_gate_softcap_enabled": true, "output_gate_softcap_limit": 2.0, "stable_gdn2_sqrt_erase_gate": true, "backbone_gdn_override": false }, "auto_map": { "AutoConfig": "configuration_memt.MemTQwen3_5MoeConfig", "AutoModelForCausalLM": "modeling_memt.MemTQwen3_5MoeForCausalLM" } }