{ "architectures": [ "LongcatCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "attention_method": "MLA", "bos_token_id": 1, "cli_factor": 2, "disable_quant_module": [], "dsa_mtp_cli": true, "eos_token_id": 2, "expert_ffn_hidden_size": 2048, "ffn_hidden_size": 12288, "hidden_size": 8192, "index_head_dim": 128, "index_init_tokens": 16, "index_k_norm_type": "rms", "index_local_tokens": 1024, "index_n_heads": 32, "index_topk": 2048, "kv_lora_rank": 512, "max_position_embeddings": 262144, "mla_scale_kv_lora": true, "mla_scale_q_lora": true, "moe_impl": "mix", "moe_switch_token_num": 1024, "moe_topk": 12, "mtp_disable_over_tokenizer": true, "mtp_num_layers": 3, "mtp_replicate_modules": true, "n_routed_experts": 768, "num_attention_heads": 64, "num_layers": 38, "oe_neighbor_num": 5, "oe_split_num": 4, "oe_vocab_size_ratio": 100.567, "q_lora_rank": 1536, "qk_nope_head_dim": 128, "qk_rope_head_dim": 64, "quantization_config": { "activation_scheme": "dynamic", "fmt": "e4m3", "ignored_layers": [ "lm_head", "model.embed_tokens", "model.layers.0.input_layernorm.0", "model.layers.0.input_layernorm.1", "model.layers.0.mlp.router.classifier", "model.layers.0.mlp.router.e_score_correction_bias", "model.layers.0.post_attention_layernorm.0", "model.layers.0.post_attention_layernorm.1", "model.layers.0.self_attn.0.indexer.k_norm", "model.layers.0.self_attn.0.indexer.weights_proj", "model.layers.0.self_attn.0.indexer.wq_b", "model.layers.0.self_attn.0.kv_a_layernorm", "model.layers.0.self_attn.0.q_a_layernorm", "model.layers.0.self_attn.1.kv_a_layernorm", "model.layers.0.self_attn.1.q_a_layernorm", "model.layers.1.input_layernorm.0", "model.layers.1.input_layernorm.1", "model.layers.1.mlp.router.classifier", "model.layers.1.mlp.router.e_score_correction_bias", "model.layers.1.post_attention_layernorm.0", "model.layers.1.post_attention_layernorm.1", "model.layers.1.self_attn.0.indexer.k_norm", "model.layers.1.self_attn.0.indexer.weights_proj", "model.layers.1.self_attn.0.indexer.wq_b", "model.layers.1.self_attn.0.kv_a_layernorm", "model.layers.1.self_attn.0.q_a_layernorm", "model.layers.1.self_attn.1.kv_a_layernorm", "model.layers.1.self_attn.1.q_a_layernorm", "model.layers.10.input_layernorm.0", "model.layers.10.input_layernorm.1", "model.layers.10.mlp.router.classifier", "model.layers.10.mlp.router.e_score_correction_bias", "model.layers.10.post_attention_layernorm.0", "model.layers.10.post_attention_layernorm.1", "model.layers.10.self_attn.0.indexer.k_norm", "model.layers.10.self_attn.0.indexer.weights_proj", "model.layers.10.self_attn.0.indexer.wq_b", "model.layers.10.self_attn.0.kv_a_layernorm", "model.layers.10.self_attn.0.q_a_layernorm", "model.layers.10.self_attn.1.kv_a_layernorm", "model.layers.10.self_attn.1.q_a_layernorm", "model.layers.11.input_layernorm.0", "model.layers.11.input_layernorm.1", "model.layers.11.mlp.router.classifier", "model.layers.11.mlp.router.e_score_correction_bias", "model.layers.11.post_attention_layernorm.0", "model.layers.11.post_attention_layernorm.1", "model.layers.11.self_attn.0.indexer.k_norm", "model.layers.11.self_attn.0.indexer.weights_proj", "model.layers.11.self_attn.0.indexer.wq_b", "model.layers.11.self_attn.0.kv_a_layernorm", "model.layers.11.self_attn.0.q_a_layernorm", "model.layers.11.self_attn.1.kv_a_layernorm", "model.layers.11.self_attn.1.q_a_layernorm", "model.layers.12.input_layernorm.0", "model.layers.12.input_layernorm.1", "model.layers.12.mlp.router.classifier", "model.layers.12.mlp.router.e_score_correction_bias", "model.layers.12.post_attention_layernorm.0", "model.layers.12.post_attention_layernorm.1", "model.layers.12.self_attn.0.indexer.k_norm", "model.layers.12.self_attn.0.indexer.weights_proj", "model.layers.12.self_attn.0.indexer.wq_b", "model.layers.12.self_attn.0.kv_a_layernorm", "model.layers.12.self_attn.0.q_a_layernorm", "model.layers.12.self_attn.1.kv_a_layernorm", "model.layers.12.self_attn.1.q_a_layernorm", "model.layers.13.input_layernorm.0", "model.layers.13.input_layernorm.1", "model.layers.13.mlp.router.classifier", "model.layers.13.mlp.router.e_score_correction_bias", "model.layers.13.post_attention_layernorm.0", "model.layers.13.post_attention_layernorm.1", "model.layers.13.self_attn.0.indexer.k_norm", "model.layers.13.self_attn.0.indexer.weights_proj", "model.layers.13.self_attn.0.indexer.wq_b", "model.layers.13.self_attn.0.kv_a_layernorm", "model.layers.13.self_attn.0.q_a_layernorm", "model.layers.13.self_attn.1.kv_a_layernorm", "model.layers.13.self_attn.1.q_a_layernorm", "model.layers.14.input_layernorm.0", "model.layers.14.input_layernorm.1", "model.layers.14.mlp.router.classifier", "model.layers.14.mlp.router.e_score_correction_bias", "model.layers.14.post_attention_layernorm.0", "model.layers.14.post_attention_layernorm.1", "model.layers.14.self_attn.0.indexer.k_norm", "model.layers.14.self_attn.0.indexer.weights_proj", "model.layers.14.self_attn.0.indexer.wq_b", "model.layers.14.self_attn.0.kv_a_layernorm", "model.layers.14.self_attn.0.q_a_layernorm", "model.layers.14.self_attn.1.kv_a_layernorm", "model.layers.14.self_attn.1.q_a_layernorm", "model.layers.15.input_layernorm.0", "model.layers.15.input_layernorm.1", "model.layers.15.mlp.router.classifier", "model.layers.15.mlp.router.e_score_correction_bias", "model.layers.15.post_attention_layernorm.0", "model.layers.15.post_attention_layernorm.1", "model.layers.15.self_attn.0.indexer.k_norm", "model.layers.15.self_attn.0.indexer.weights_proj", "model.layers.15.self_attn.0.indexer.wq_b", "model.layers.15.self_attn.0.kv_a_layernorm", "model.layers.15.self_attn.0.q_a_layernorm", "model.layers.15.self_attn.1.kv_a_layernorm", "model.layers.15.self_attn.1.q_a_layernorm", "model.layers.16.input_layernorm.0", "model.layers.16.input_layernorm.1", "model.layers.16.mlp.router.classifier", "model.layers.16.mlp.router.e_score_correction_bias", "model.layers.16.post_attention_layernorm.0", "model.layers.16.post_attention_layernorm.1", "model.layers.16.self_attn.0.indexer.k_norm", "model.layers.16.self_attn.0.indexer.weights_proj", "model.layers.16.self_attn.0.indexer.wq_b", "model.layers.16.self_attn.0.kv_a_layernorm", "model.layers.16.self_attn.0.q_a_layernorm", "model.layers.16.self_attn.1.kv_a_layernorm", "model.layers.16.self_attn.1.q_a_layernorm", "model.layers.17.input_layernorm.0", "model.layers.17.input_layernorm.1", "model.layers.17.mlp.router.classifier", "model.layers.17.mlp.router.e_score_correction_bias", "model.layers.17.post_attention_layernorm.0", "model.layers.17.post_attention_layernorm.1", "model.layers.17.self_attn.0.indexer.k_norm", "model.layers.17.self_attn.0.indexer.weights_proj", "model.layers.17.self_attn.0.indexer.wq_b", "model.layers.17.self_attn.0.kv_a_layernorm", "model.layers.17.self_attn.0.q_a_layernorm", "model.layers.17.self_attn.1.kv_a_layernorm", "model.layers.17.self_attn.1.q_a_layernorm", "model.layers.18.input_layernorm.0", "model.layers.18.input_layernorm.1", "model.layers.18.mlp.router.classifier", "model.layers.18.mlp.router.e_score_correction_bias", "model.layers.18.post_attention_layernorm.0", "model.layers.18.post_attention_layernorm.1", "model.layers.18.self_attn.0.indexer.k_norm", "model.layers.18.self_attn.0.indexer.weights_proj", "model.layers.18.self_attn.0.indexer.wq_b", "model.layers.18.self_attn.0.kv_a_layernorm", "model.layers.18.self_attn.0.q_a_layernorm", "model.layers.18.self_attn.1.kv_a_layernorm", "model.layers.18.self_attn.1.q_a_layernorm", "model.layers.19.input_layernorm.0", "model.layers.19.input_layernorm.1", "model.layers.19.mlp.router.classifier", "model.layers.19.mlp.router.e_score_correction_bias", "model.layers.19.post_attention_layernorm.0", "model.layers.19.post_attention_layernorm.1", "model.layers.19.self_attn.0.indexer.k_norm", "model.layers.19.self_attn.0.indexer.weights_proj", "model.layers.19.self_attn.0.indexer.wq_b", "model.layers.19.self_attn.0.kv_a_layernorm", "model.layers.19.self_attn.0.q_a_layernorm", "model.layers.19.self_attn.1.kv_a_layernorm", "model.layers.19.self_attn.1.q_a_layernorm", "model.layers.2.input_layernorm.0", "model.layers.2.input_layernorm.1", "model.layers.2.mlp.router.classifier", "model.layers.2.mlp.router.e_score_correction_bias", "model.layers.2.post_attention_layernorm.0", "model.layers.2.post_attention_layernorm.1", "model.layers.2.self_attn.0.indexer.k_norm", "model.layers.2.self_attn.0.indexer.weights_proj", "model.layers.2.self_attn.0.indexer.wq_b", "model.layers.2.self_attn.0.kv_a_layernorm", "model.layers.2.self_attn.0.q_a_layernorm", "model.layers.2.self_attn.1.kv_a_layernorm", "model.layers.2.self_attn.1.q_a_layernorm", "model.layers.20.input_layernorm.0", "model.layers.20.input_layernorm.1", "model.layers.20.mlp.router.classifier", "model.layers.20.mlp.router.e_score_correction_bias", "model.layers.20.post_attention_layernorm.0", "model.layers.20.post_attention_layernorm.1", "model.layers.20.self_attn.0.indexer.k_norm", "model.layers.20.self_attn.0.indexer.weights_proj", "model.layers.20.self_attn.0.indexer.wq_b", "model.layers.20.self_attn.0.kv_a_layernorm", "model.layers.20.self_attn.0.q_a_layernorm", "model.layers.20.self_attn.1.kv_a_layernorm", "model.layers.20.self_attn.1.q_a_layernorm", "model.layers.21.input_layernorm.0", "model.layers.21.input_layernorm.1", "model.layers.21.mlp.router.classifier", "model.layers.21.mlp.router.e_score_correction_bias", "model.layers.21.post_attention_layernorm.0", "model.layers.21.post_attention_layernorm.1", "model.layers.21.self_attn.0.indexer.k_norm", "model.layers.21.self_attn.0.indexer.weights_proj", "model.layers.21.self_attn.0.indexer.wq_b", "model.layers.21.self_attn.0.kv_a_layernorm", "model.layers.21.self_attn.0.q_a_layernorm", "model.layers.21.self_attn.1.kv_a_layernorm", "model.layers.21.self_attn.1.q_a_layernorm", "model.layers.22.input_layernorm.0", "model.layers.22.input_layernorm.1", "model.layers.22.mlp.router.classifier", "model.layers.22.mlp.router.e_score_correction_bias", "model.layers.22.post_attention_layernorm.0", "model.layers.22.post_attention_layernorm.1", "model.layers.22.self_attn.0.indexer.k_norm", "model.layers.22.self_attn.0.indexer.weights_proj", "model.layers.22.self_attn.0.indexer.wq_b", "model.layers.22.self_attn.0.kv_a_layernorm", "model.layers.22.self_attn.0.q_a_layernorm", "model.layers.22.self_attn.1.kv_a_layernorm", "model.layers.22.self_attn.1.q_a_layernorm", "model.layers.23.input_layernorm.0", "model.layers.23.input_layernorm.1", "model.layers.23.mlp.router.classifier", "model.layers.23.mlp.router.e_score_correction_bias", "model.layers.23.post_attention_layernorm.0", "model.layers.23.post_attention_layernorm.1", "model.layers.23.self_attn.0.indexer.k_norm", "model.layers.23.self_attn.0.indexer.weights_proj", "model.layers.23.self_attn.0.indexer.wq_b", "model.layers.23.self_attn.0.kv_a_layernorm", "model.layers.23.self_attn.0.q_a_layernorm", "model.layers.23.self_attn.1.kv_a_layernorm", "model.layers.23.self_attn.1.q_a_layernorm", "model.layers.24.input_layernorm.0", "model.layers.24.input_layernorm.1", "model.layers.24.mlp.router.classifier", "model.layers.24.mlp.router.e_score_correction_bias", "model.layers.24.post_attention_layernorm.0", "model.layers.24.post_attention_layernorm.1", "model.layers.24.self_attn.0.indexer.k_norm", "model.layers.24.self_attn.0.indexer.weights_proj", "model.layers.24.self_attn.0.indexer.wq_b", "model.layers.24.self_attn.0.kv_a_layernorm", "model.layers.24.self_attn.0.q_a_layernorm", "model.layers.24.self_attn.1.kv_a_layernorm", "model.layers.24.self_attn.1.q_a_layernorm", "model.layers.25.input_layernorm.0", "model.layers.25.input_layernorm.1", "model.layers.25.mlp.router.classifier", "model.layers.25.mlp.router.e_score_correction_bias", "model.layers.25.post_attention_layernorm.0", "model.layers.25.post_attention_layernorm.1", "model.layers.25.self_attn.0.indexer.k_norm", "model.layers.25.self_attn.0.indexer.weights_proj", "model.layers.25.self_attn.0.indexer.wq_b", "model.layers.25.self_attn.0.kv_a_layernorm", "model.layers.25.self_attn.0.q_a_layernorm", "model.layers.25.self_attn.1.kv_a_layernorm", "model.layers.25.self_attn.1.q_a_layernorm", "model.layers.26.input_layernorm.0", "model.layers.26.input_layernorm.1", "model.layers.26.mlp.router.classifier", "model.layers.26.mlp.router.e_score_correction_bias", "model.layers.26.post_attention_layernorm.0", "model.layers.26.post_attention_layernorm.1", "model.layers.26.self_attn.0.indexer.k_norm", "model.layers.26.self_attn.0.indexer.weights_proj", "model.layers.26.self_attn.0.indexer.wq_b", "model.layers.26.self_attn.0.kv_a_layernorm", "model.layers.26.self_attn.0.q_a_layernorm", "model.layers.26.self_attn.1.kv_a_layernorm", "model.layers.26.self_attn.1.q_a_layernorm", "model.layers.27.input_layernorm.0", "model.layers.27.input_layernorm.1", "model.layers.27.mlp.router.classifier", "model.layers.27.mlp.router.e_score_correction_bias", "model.layers.27.post_attention_layernorm.0", "model.layers.27.post_attention_layernorm.1", "model.layers.27.self_attn.0.indexer.k_norm", "model.layers.27.self_attn.0.indexer.weights_proj", "model.layers.27.self_attn.0.indexer.wq_b", "model.layers.27.self_attn.0.kv_a_layernorm", "model.layers.27.self_attn.0.q_a_layernorm", "model.layers.27.self_attn.1.kv_a_layernorm", "model.layers.27.self_attn.1.q_a_layernorm", "model.layers.28.input_layernorm.0", "model.layers.28.input_layernorm.1", "model.layers.28.mlp.router.classifier", "model.layers.28.mlp.router.e_score_correction_bias", "model.layers.28.post_attention_layernorm.0", "model.layers.28.post_attention_layernorm.1", "model.layers.28.self_attn.0.indexer.k_norm", "model.layers.28.self_attn.0.indexer.weights_proj", "model.layers.28.self_attn.0.indexer.wq_b", "model.layers.28.self_attn.0.kv_a_layernorm", "model.layers.28.self_attn.0.q_a_layernorm", "model.layers.28.self_attn.1.kv_a_layernorm", "model.layers.28.self_attn.1.q_a_layernorm", "model.layers.29.input_layernorm.0", "model.layers.29.input_layernorm.1", "model.layers.29.mlp.router.classifier", "model.layers.29.mlp.router.e_score_correction_bias", "model.layers.29.post_attention_layernorm.0", "model.layers.29.post_attention_layernorm.1", "model.layers.29.self_attn.0.indexer.k_norm", "model.layers.29.self_attn.0.indexer.weights_proj", "model.layers.29.self_attn.0.indexer.wq_b", "model.layers.29.self_attn.0.kv_a_layernorm", "model.layers.29.self_attn.0.q_a_layernorm", "model.layers.29.self_attn.1.kv_a_layernorm", "model.layers.29.self_attn.1.q_a_layernorm", "model.layers.3.input_layernorm.0", "model.layers.3.input_layernorm.1", "model.layers.3.mlp.router.classifier", "model.layers.3.mlp.router.e_score_correction_bias", "model.layers.3.post_attention_layernorm.0", "model.layers.3.post_attention_layernorm.1", "model.layers.3.self_attn.0.indexer.k_norm", "model.layers.3.self_attn.0.indexer.weights_proj", "model.layers.3.self_attn.0.indexer.wq_b", "model.layers.3.self_attn.0.kv_a_layernorm", "model.layers.3.self_attn.0.q_a_layernorm", "model.layers.3.self_attn.1.kv_a_layernorm", "model.layers.3.self_attn.1.q_a_layernorm", "model.layers.30.input_layernorm.0", "model.layers.30.input_layernorm.1", "model.layers.30.mlp.router.classifier", "model.layers.30.mlp.router.e_score_correction_bias", "model.layers.30.post_attention_layernorm.0", "model.layers.30.post_attention_layernorm.1", "model.layers.30.self_attn.0.indexer.k_norm", "model.layers.30.self_attn.0.indexer.weights_proj", "model.layers.30.self_attn.0.indexer.wq_b", "model.layers.30.self_attn.0.kv_a_layernorm", "model.layers.30.self_attn.0.q_a_layernorm", "model.layers.30.self_attn.1.kv_a_layernorm", "model.layers.30.self_attn.1.q_a_layernorm", "model.layers.31.input_layernorm.0", "model.layers.31.input_layernorm.1", "model.layers.31.mlp.router.classifier", "model.layers.31.mlp.router.e_score_correction_bias", "model.layers.31.post_attention_layernorm.0", "model.layers.31.post_attention_layernorm.1", "model.layers.31.self_attn.0.indexer.k_norm", "model.layers.31.self_attn.0.indexer.weights_proj", "model.layers.31.self_attn.0.indexer.wq_b", "model.layers.31.self_attn.0.kv_a_layernorm", "model.layers.31.self_attn.0.q_a_layernorm", "model.layers.31.self_attn.1.kv_a_layernorm", "model.layers.31.self_attn.1.q_a_layernorm", "model.layers.32.input_layernorm.0", "model.layers.32.input_layernorm.1", "model.layers.32.mlp.router.classifier", "model.layers.32.mlp.router.e_score_correction_bias", "model.layers.32.post_attention_layernorm.0", "model.layers.32.post_attention_layernorm.1", "model.layers.32.self_attn.0.indexer.k_norm", "model.layers.32.self_attn.0.indexer.weights_proj", "model.layers.32.self_attn.0.indexer.wq_b", "model.layers.32.self_attn.0.kv_a_layernorm", "model.layers.32.self_attn.0.q_a_layernorm", "model.layers.32.self_attn.1.kv_a_layernorm", "model.layers.32.self_attn.1.q_a_layernorm", "model.layers.33.input_layernorm.0", "model.layers.33.input_layernorm.1", "model.layers.33.mlp.router.classifier", "model.layers.33.mlp.router.e_score_correction_bias", "model.layers.33.post_attention_layernorm.0", "model.layers.33.post_attention_layernorm.1", "model.layers.33.self_attn.0.indexer.k_norm", "model.layers.33.self_attn.0.indexer.weights_proj", "model.layers.33.self_attn.0.indexer.wq_b", "model.layers.33.self_attn.0.kv_a_layernorm", "model.layers.33.self_attn.0.q_a_layernorm", "model.layers.33.self_attn.1.kv_a_layernorm", "model.layers.33.self_attn.1.q_a_layernorm", "model.layers.34.input_layernorm.0", "model.layers.34.input_layernorm.1", "model.layers.34.mlp.router.classifier", "model.layers.34.mlp.router.e_score_correction_bias", "model.layers.34.post_attention_layernorm.0", "model.layers.34.post_attention_layernorm.1", "model.layers.34.self_attn.0.indexer.k_norm", "model.layers.34.self_attn.0.indexer.weights_proj", "model.layers.34.self_attn.0.indexer.wq_b", "model.layers.34.self_attn.0.kv_a_layernorm", "model.layers.34.self_attn.0.q_a_layernorm", "model.layers.34.self_attn.1.kv_a_layernorm", "model.layers.34.self_attn.1.q_a_layernorm", "model.layers.35.input_layernorm.0", "model.layers.35.input_layernorm.1", "model.layers.35.mlp.router.classifier", "model.layers.35.mlp.router.e_score_correction_bias", "model.layers.35.post_attention_layernorm.0", "model.layers.35.post_attention_layernorm.1", "model.layers.35.self_attn.0.indexer.k_norm", "model.layers.35.self_attn.0.indexer.weights_proj", "model.layers.35.self_attn.0.indexer.wq_b", "model.layers.35.self_attn.0.kv_a_layernorm", "model.layers.35.self_attn.0.q_a_layernorm", "model.layers.35.self_attn.1.kv_a_layernorm", "model.layers.35.self_attn.1.q_a_layernorm", "model.layers.36.input_layernorm.0", "model.layers.36.input_layernorm.1", "model.layers.36.mlp.router.classifier", "model.layers.36.mlp.router.e_score_correction_bias", "model.layers.36.post_attention_layernorm.0", "model.layers.36.post_attention_layernorm.1", "model.layers.36.self_attn.0.indexer.k_norm", "model.layers.36.self_attn.0.indexer.weights_proj", "model.layers.36.self_attn.0.indexer.wq_b", "model.layers.36.self_attn.0.kv_a_layernorm", "model.layers.36.self_attn.0.q_a_layernorm", "model.layers.36.self_attn.1.kv_a_layernorm", "model.layers.36.self_attn.1.q_a_layernorm", "model.layers.37.input_layernorm.0", "model.layers.37.input_layernorm.1", "model.layers.37.mlp.router.classifier", "model.layers.37.mlp.router.e_score_correction_bias", "model.layers.37.post_attention_layernorm.0", "model.layers.37.post_attention_layernorm.1", "model.layers.37.self_attn.0.indexer.k_norm", "model.layers.37.self_attn.0.indexer.weights_proj", "model.layers.37.self_attn.0.indexer.wq_b", "model.layers.37.self_attn.0.kv_a_layernorm", "model.layers.37.self_attn.0.q_a_layernorm", "model.layers.37.self_attn.1.kv_a_layernorm", "model.layers.37.self_attn.1.q_a_layernorm", "model.layers.4.input_layernorm.0", "model.layers.4.input_layernorm.1", "model.layers.4.mlp.router.classifier", "model.layers.4.mlp.router.e_score_correction_bias", "model.layers.4.post_attention_layernorm.0", "model.layers.4.post_attention_layernorm.1", "model.layers.4.self_attn.0.indexer.k_norm", "model.layers.4.self_attn.0.indexer.weights_proj", "model.layers.4.self_attn.0.indexer.wq_b", "model.layers.4.self_attn.0.kv_a_layernorm", "model.layers.4.self_attn.0.q_a_layernorm", "model.layers.4.self_attn.1.kv_a_layernorm", "model.layers.4.self_attn.1.q_a_layernorm", "model.layers.5.input_layernorm.0", "model.layers.5.input_layernorm.1", "model.layers.5.mlp.router.classifier", "model.layers.5.mlp.router.e_score_correction_bias", "model.layers.5.post_attention_layernorm.0", "model.layers.5.post_attention_layernorm.1", "model.layers.5.self_attn.0.indexer.k_norm", "model.layers.5.self_attn.0.indexer.weights_proj", "model.layers.5.self_attn.0.indexer.wq_b", "model.layers.5.self_attn.0.kv_a_layernorm", "model.layers.5.self_attn.0.q_a_layernorm", "model.layers.5.self_attn.1.kv_a_layernorm", "model.layers.5.self_attn.1.q_a_layernorm", "model.layers.6.input_layernorm.0", "model.layers.6.input_layernorm.1", "model.layers.6.mlp.router.classifier", "model.layers.6.mlp.router.e_score_correction_bias", "model.layers.6.post_attention_layernorm.0", "model.layers.6.post_attention_layernorm.1", "model.layers.6.self_attn.0.indexer.k_norm", "model.layers.6.self_attn.0.indexer.weights_proj", "model.layers.6.self_attn.0.indexer.wq_b", "model.layers.6.self_attn.0.kv_a_layernorm", "model.layers.6.self_attn.0.q_a_layernorm", "model.layers.6.self_attn.1.kv_a_layernorm", "model.layers.6.self_attn.1.q_a_layernorm", "model.layers.7.input_layernorm.0", "model.layers.7.input_layernorm.1", "model.layers.7.mlp.router.classifier", "model.layers.7.mlp.router.e_score_correction_bias", "model.layers.7.post_attention_layernorm.0", "model.layers.7.post_attention_layernorm.1", "model.layers.7.self_attn.0.indexer.k_norm", "model.layers.7.self_attn.0.indexer.weights_proj", "model.layers.7.self_attn.0.indexer.wq_b", "model.layers.7.self_attn.0.kv_a_layernorm", "model.layers.7.self_attn.0.q_a_layernorm", "model.layers.7.self_attn.1.kv_a_layernorm", "model.layers.7.self_attn.1.q_a_layernorm", "model.layers.8.input_layernorm.0", "model.layers.8.input_layernorm.1", "model.layers.8.mlp.router.classifier", "model.layers.8.mlp.router.e_score_correction_bias", "model.layers.8.post_attention_layernorm.0", "model.layers.8.post_attention_layernorm.1", "model.layers.8.self_attn.0.indexer.k_norm", "model.layers.8.self_attn.0.indexer.weights_proj", "model.layers.8.self_attn.0.indexer.wq_b", "model.layers.8.self_attn.0.kv_a_layernorm", "model.layers.8.self_attn.0.q_a_layernorm", "model.layers.8.self_attn.1.kv_a_layernorm", "model.layers.8.self_attn.1.q_a_layernorm", "model.layers.9.input_layernorm.0", "model.layers.9.input_layernorm.1", "model.layers.9.mlp.router.classifier", "model.layers.9.mlp.router.e_score_correction_bias", "model.layers.9.post_attention_layernorm.0", "model.layers.9.post_attention_layernorm.1", "model.layers.9.self_attn.0.indexer.k_norm", "model.layers.9.self_attn.0.indexer.weights_proj", "model.layers.9.self_attn.0.indexer.wq_b", "model.layers.9.self_attn.0.kv_a_layernorm", "model.layers.9.self_attn.0.q_a_layernorm", "model.layers.9.self_attn.1.kv_a_layernorm", "model.layers.9.self_attn.1.q_a_layernorm", "model.mtp.embed_tokens", "model.mtp.layers.0.enorm.m", "model.mtp.layers.0.hnorm.m", "model.mtp.layers.0.input_layernorm", "model.mtp.layers.0.post_attention_layernorm", "model.mtp.layers.0.self_attn.indexer.k_norm", "model.mtp.layers.0.self_attn.kv_a_layernorm", "model.mtp.layers.0.self_attn.q_a_layernorm", "model.mtp.ngram_embeddings.embedders.0", "model.mtp.ngram_embeddings.embedders.1", "model.mtp.ngram_embeddings.embedders.10", "model.mtp.ngram_embeddings.embedders.11", "model.mtp.ngram_embeddings.embedders.12", "model.mtp.ngram_embeddings.embedders.13", "model.mtp.ngram_embeddings.embedders.14", "model.mtp.ngram_embeddings.embedders.15", "model.mtp.ngram_embeddings.embedders.2", "model.mtp.ngram_embeddings.embedders.3", "model.mtp.ngram_embeddings.embedders.4", "model.mtp.ngram_embeddings.embedders.5", "model.mtp.ngram_embeddings.embedders.6", "model.mtp.ngram_embeddings.embedders.7", "model.mtp.ngram_embeddings.embedders.8", "model.mtp.ngram_embeddings.embedders.9", "model.mtp.ngram_embeddings.post_projs.0", "model.mtp.ngram_embeddings.post_projs.1", "model.mtp.ngram_embeddings.post_projs.10", "model.mtp.ngram_embeddings.post_projs.11", "model.mtp.ngram_embeddings.post_projs.12", "model.mtp.ngram_embeddings.post_projs.13", "model.mtp.ngram_embeddings.post_projs.14", "model.mtp.ngram_embeddings.post_projs.15", "model.mtp.ngram_embeddings.post_projs.2", "model.mtp.ngram_embeddings.post_projs.3", "model.mtp.ngram_embeddings.post_projs.4", "model.mtp.ngram_embeddings.post_projs.5", "model.mtp.ngram_embeddings.post_projs.6", "model.mtp.ngram_embeddings.post_projs.7", "model.mtp.ngram_embeddings.post_projs.8", "model.mtp.ngram_embeddings.post_projs.9", "model.mtp.norm", "model.ngram_embeddings.embedders.0", "model.ngram_embeddings.embedders.1", "model.ngram_embeddings.embedders.10", "model.ngram_embeddings.embedders.11", "model.ngram_embeddings.embedders.12", "model.ngram_embeddings.embedders.13", "model.ngram_embeddings.embedders.14", "model.ngram_embeddings.embedders.15", "model.ngram_embeddings.embedders.2", "model.ngram_embeddings.embedders.3", "model.ngram_embeddings.embedders.4", "model.ngram_embeddings.embedders.5", "model.ngram_embeddings.embedders.6", "model.ngram_embeddings.embedders.7", "model.ngram_embeddings.embedders.8", "model.ngram_embeddings.embedders.9", "model.ngram_embeddings.post_projs.0", "model.ngram_embeddings.post_projs.1", "model.ngram_embeddings.post_projs.10", "model.ngram_embeddings.post_projs.11", "model.ngram_embeddings.post_projs.12", "model.ngram_embeddings.post_projs.13", "model.ngram_embeddings.post_projs.14", "model.ngram_embeddings.post_projs.15", "model.ngram_embeddings.post_projs.2", "model.ngram_embeddings.post_projs.3", "model.ngram_embeddings.post_projs.4", "model.ngram_embeddings.post_projs.5", "model.ngram_embeddings.post_projs.6", "model.ngram_embeddings.post_projs.7", "model.ngram_embeddings.post_projs.8", "model.ngram_embeddings.post_projs.9", "model.norm" ], "quant_method": "fp8", "weight_block_size": [ 128, 128 ] }, "rms_norm_eps": 1e-05, "rope_scaling": { "beta_fast": 32, "beta_slow": 1, "factor": 120, "mscale": 1, "mscale_all_dim": 1, "original_max_position_embeddings": 8192, "rope_type": "deepseek_yarn" }, "rope_theta": 1000000.0, "routed_scaling_factor": 9, "use_cache": true, "use_mla": 1, "v_head_dim": 128, "vocab_size": 163840, "zero_expert_num": 128, "zero_expert_type": "identity" }