config.json

{
    "architectures": [
        "LongcatFlashNgramForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "auto_map": {
        "AutoConfig": "configuration_longcat_ngram.LongcatFlashNgramConfig",
        "AutoModel": "modeling_longcat_ngram.LongcatFlashNgramModel",
        "AutoModelForCausalLM": "modeling_longcat_ngram.LongcatFlashNgramForCausalLM"
    },
    "bos_token_id": 1,
    "emb_neighbor_num": 4,
    "emb_split_num": 4,
    "eos_token_id": 2,
    "expert_ffn_hidden_size": 1024,
    "ffn_hidden_size": 6144,
    "hidden_size": 3072,
    "kv_lora_rank": 512,
    "max_position_embeddings": 327680,
    "mla_scale_kv_lora": true,
    "mla_scale_q_lora": true,
    "model_type": "longcat_flash_ngram",
    "moe_topk": 12,
    "n_routed_experts": 256,
    "ngram_vocab_size_ratio": 78,
    "num_attention_heads": 32,
    "num_layers": 14,
    "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
        }
    },
    "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
        }
    },
    "rms_norm_eps": 1e-05,
    "rope_scaling": {
        "original_max_position_embeddings": 32768,
        "rope_type": "yarn",
        "factor": 10,
        "beta_fast": 32,
        "beta_slow": 1,
        "mscale": 1,
        "mscale_all_dim": 1
    },
    "rope_theta": 5000000.0,
    "routed_scaling_factor": 6.0,
    "torch_dtype": "bfloat16",
    "transformers_version": "4.57.6",
    "use_cache": true,
    "v_head_dim": 128,
    "vocab_size": 131072,
    "zero_expert_num": 128,
    "zero_expert_type": "identity"
}