{
  "architectures": [
    "BailingMoeV2_5ForCausalLM"
  ],
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_bailing_moe_v2_5.BailingMoeV2_5Config",
    "AutoModel": "modeling_bailing_moe_v2_5.BailingMoeV2_5Model",
    "AutoModelForCausalLM": "modeling_bailing_moe_v2_5.BailingMoeV2_5ForCausalLM"
  },
  "embedding_dropout": 0.0,
  "eos_token_id": 156895,
  "first_k_dense_replace": 1,
  "group_norm_size": 4,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 9216,
  "kv_lora_rank": 512,
  "layer_group_size": 8,
  "linear_silu": false,
  "max_position_embeddings": 131072,
  "max_window_layers": 20,
  "moe_intermediate_size": 1024,
  "moe_router_enable_expert_bias": true,
  "moe_shared_expert_intermediate_size": 1024,
  "mtp_loss_scaling_factor": 0,
  "n_group": 8,
  "num_attention_heads": 32,
  "num_experts": 256,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 32,
  "num_key_value_heads": 32,
  "num_kv_heads_for_linear_attn": 32,
  "num_nextn_predict_layers": 1,
  "num_shared_experts": 1,
  "output_dropout": 0.0,
  "output_router_logits": false,
  "pad_token_id": 156892,
  "partial_rotary_factor": 0.5,
  "q_lora_rank": 1536,
  "qk_head_dim": 192,
  "qk_nope_head_dim": 128,
  "qk_rope_head_dim": 64,
  "rms_norm_eps": 1e-06,
  "rope_interleave": true,
  "rope_scaling": null,
  "rope_theta": 6000000,
  "rotary_dim": 64,
  "routed_scaling_factor": 2.5,
  "router_dtype": "fp32",
  "score_function": "sigmoid",
  "scoring_func": "sigmoid",
  "seq_aux": true,
  "tie_word_embeddings": false,
  "topk_group": 4,
  "topk_method": "noaux_tc",
  "transformers_version": "4.56.2",
  "use_bias": false,
  "use_cache": true,
  "use_qk_norm": true,
  "use_qkv_bias": false,
  "v_head_dim": 128,
  "vocab_size": 157184,
  "model_type": "bailing_hybrid",
  "torch_dtype": "bfloat16",
  "quantization_config": {
    "quant_method": "compressed-tensors",
    "format": "pack-quantized",
    "config_groups": {
      "group_0": {
        "targets": [
          "Linear"
        ],
        "weights": {
          "num_bits": 4,
          "type": "int",
          "symmetric": true,
          "strategy": "group",
          "dynamic": false,
          "observer": "minmax",
          "group_size": 32
        }
      }
    },
    "ignore": [
      "re:.*lm_head.*",
      "re:.*self_attn.*",
      "re:.*attention.*",
      "re:.*(mlp|shared_experts)\\.(gate|up|gate_up|down)_proj.*",
      "re:.*layers\\.\\d+\\.(gate|up|gate_up|down)_proj.*"
    ],
    "quantization_status": "compressed"
  }
}