{ "architectures": [ "LongcatCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "vocab_size": 163840, "hidden_size": 8192, "ffn_hidden_size": 12288, "expert_ffn_hidden_size": 2048, "num_layers": 38, "num_attention_heads": 64, "kv_lora_rank": 512, "q_lora_rank": 1536, "qk_rope_head_dim": 64, "v_head_dim": 128, "qk_nope_head_dim": 128, "mla_scale_q_lora": true, "mla_scale_kv_lora": true, "routed_scaling_factor": 9, "n_routed_experts": 768, "max_position_embeddings": 262144, "rms_norm_eps": 1e-5, "use_cache": true, "bos_token_id": 1, "eos_token_id": 2, "rope_theta": 1000000.0, "rope_scaling": { "original_max_position_embeddings": 8192, "rope_type": "deepseek_yarn", "factor": 120, "beta_fast": 32, "beta_slow": 1, "mscale": 1, "mscale_all_dim": 1 }, "attention_method": "MLA", "zero_expert_num": 128, "zero_expert_type": "identity", "moe_topk": 12, "use_mla": 1, "moe_switch_token_num": 1024, "moe_impl": "mix", "oe_vocab_size_ratio": 100.567, "oe_neighbor_num": 5, "oe_split_num": 4, "mtp_num_layers": 3, "mtp_replicate_modules": true, "mtp_disable_over_tokenizer": true, "index_n_heads": 32, "index_head_dim": 128, "index_topk": 2048, "index_k_norm_type": "rms", "cli_factor": 2, "dsa_mtp_cli": true, "index_local_tokens": 1024, "index_init_tokens": 16 }