{
  "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": 156892,
  "first_k_dense_replace": 4,
  "group_norm_size": 8,
  "head_dim": 128,
  "hidden_act": "silu",
  "hidden_size": 8192,
  "initializer_range": 0.02,
  "intermediate_size": 18432,
  "kv_lora_rank": 512,
  "layer_group_size": 8,
  "linear_silu": false,
  "max_position_embeddings": 131072,
  "max_window_layers": 20,
  "model_type": "bailing_hybrid",
  "moe_intermediate_size": 2048,
  "moe_router_enable_expert_bias": true,
  "moe_shared_expert_intermediate_size": 2048,
  "mtp_loss_scaling_factor": 0,
  "n_group": 8,
  "num_attention_heads": 64,
  "num_experts": 256,
  "num_experts_per_tok": 8,
  "num_hidden_layers": 80,
  "num_key_value_heads": 64,
  "num_kv_heads_for_linear_attn": 64,
  "num_nextn_predict_layers": 0,
  "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,
  "quantization_config": {
    "config_groups": {
      "FP8_DYNAMIC": {
        "format": "float-quantized",
        "input_activations": {
          "actorder": null,
          "block_structure": null,
          "dynamic": true,
          "group_size": null,
          "num_bits": 8,
          "observer": null,
          "observer_kwargs": {},
          "strategy": "token",
          "symmetric": true,
          "type": "float"
        },
        "output_activations": null,
        "targets": [
          "Linear"
        ],
        "weights": {
          "actorder": null,
          "block_structure": null,
          "dynamic": false,
          "group_size": null,
          "num_bits": 8,
          "observer": "static_minmax",
          "observer_kwargs": {},
          "strategy": "channel",
          "symmetric": true,
          "type": "float"
        }
      }
    },
    "format": "float-quantized",
    "global_compression_ratio": null,
    "ignore": [
      "re:.*mlp.gate$",
      "lm_head",
      "model.word_embeddings"
    ],
    "kv_cache_scheme": null,
    "quant_method": "compressed-tensors",
    "quantization_status": "compressed",
    "sparsity_config": {},
    "transform_config": {},
    "version": "0.13.0"
  },
  "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",
  "torch_dtype": "bfloat16",
  "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
}