config.json

{
    "architectures": [
        "LongcatFlashForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "attention_method": "MLA",
    "auto_map": {
        "AutoConfig": "configuration_longcat_flash.LongcatFlashConfig",
        "AutoModel": "modeling_longcat_flash.LongcatFlashModel",
        "AutoModelForCausalLM": "modeling_longcat_flash.LongcatFlashForCausalLM"
    },
    "bos_token_id": 1,
    "eos_token_id": 2,
    "expert_ffn_hidden_size": 2048,
    "ffn_hidden_size": 12288,
    "hidden_size": 6144,
    "kv_lora_rank": 512,
    "max_position_embeddings": 131072,
    "mla_scale_kv_lora": true,
    "mla_scale_q_lora": true,
    "model_type": "longcat_flash",
    "moe_topk": 12,
    "n_routed_experts": 512,
    "num_attention_heads": 64,
    "num_layers": 28,
    "q_lora_rank": 1536,
    "qk_nope_head_dim": 128,
    "qk_rope_head_dim": 64,
    "quantization": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine",
        "model.layers.0.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        }
    },
    "quantization_config": {
        "group_size": 64,
        "bits": 4,
        "mode": "affine",
        "model.layers.0.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.1.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.2.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.3.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.4.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.5.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.6.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.7.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.8.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.9.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.10.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.11.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.12.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.13.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.14.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.15.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.16.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.17.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.18.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.19.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.20.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.21.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.22.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.23.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.24.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.25.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.26.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        },
        "model.layers.27.mlp.router.classifier": {
            "group_size": 64,
            "bits": 8
        }
    },
    "rms_norm_eps": 1e-05,
    "rope_theta": 10000000.0,
    "routed_scaling_factor": 6.0,
    "use_cache": true,
    "v_head_dim": 128,
    "vocab_size": 131072,
    "zero_expert_num": 256,
    "zero_expert_type": "identity"
}