{
  "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"
  },
  "vocab_size": 131072,
  "hidden_size": 3072,
  "ffn_hidden_size": 6144,
  "expert_ffn_hidden_size": 1024,
  "num_layers": 14,
  "num_attention_heads": 32,
  "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": 6.0,
  "n_routed_experts": 256,
  "rms_norm_eps": 1e-5,
  "use_cache": true,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "rope_theta": 5000000.0,
  "max_position_embeddings": 327680,
  "rope_scaling": {
      "original_max_position_embeddings": 32768,
      "rope_type": "yarn",
      "factor": 10,
      "beta_fast": 32,
      "beta_slow": 1,
      "mscale": 1,
      "mscale_all_dim": 1
  },
  "zero_expert_num": 128,
  "zero_expert_type": "identity",
  "moe_topk": 12,
  "ngram_vocab_size_ratio": 78,
  "emb_neighbor_num": 4,
  "emb_split_num": 4,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.57.6"
}