{ "architectures": [ "BailingMoeV2ForCausalLM" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_bailing_moe_v2.BailingMoeV2Config", "AutoModel": "modeling_bailing_moe_v2.BailingMoeV2Model", "AutoModelForCausalLM": "modeling_bailing_moe_v2.BailingMoeV2ForCausalLM" }, "dtype": "bfloat16", "embedding_dropout": 0.0, "eos_token_id": 156895, "first_k_dense_replace": 1, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 9216, "max_position_embeddings": 32768, "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, "norm_topk_prob": true, "num_attention_heads": 32, "num_experts": 256, "num_experts_per_tok": 8, "num_hidden_layers": 32, "num_key_value_heads": 4, "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, "quantization_config": { "config_groups": { "group_0": { "format": "pack-quantized", "input_activations": null, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": null, "block_structure": null, "dynamic": false, "group_size": 32, "num_bits": 4, "observer": "mse", "observer_kwargs": {}, "strategy": "group", "symmetric": true, "type": "int" } } }, "format": "pack-quantized", "global_compression_ratio": null, "ignore": [ "model.layers.0.attention.query_key_value", "model.layers.0.attention.dense", "model.layers.0.mlp.gate_proj", "model.layers.0.mlp.up_proj", "model.layers.0.mlp.down_proj", "model.layers.1.attention.dense", "model.layers.1.mlp.shared_experts.gate_proj", "model.layers.1.mlp.shared_experts.up_proj", "model.layers.1.mlp.shared_experts.down_proj", "model.layers.2.attention.dense", "model.layers.2.mlp.shared_experts.gate_proj", "model.layers.2.mlp.shared_experts.up_proj", "model.layers.2.mlp.shared_experts.down_proj", "model.layers.3.attention.dense", "model.layers.3.mlp.shared_experts.gate_proj", "model.layers.3.mlp.shared_experts.up_proj", "model.layers.3.mlp.shared_experts.down_proj", "model.layers.4.attention.dense", "model.layers.4.mlp.shared_experts.gate_proj", "model.layers.4.mlp.shared_experts.up_proj", "model.layers.4.mlp.shared_experts.down_proj", "model.layers.5.attention.dense", "model.layers.5.mlp.shared_experts.gate_proj", "model.layers.5.mlp.shared_experts.up_proj", "model.layers.5.mlp.shared_experts.down_proj", "model.layers.6.attention.dense", "model.layers.6.mlp.shared_experts.gate_proj", "model.layers.6.mlp.shared_experts.up_proj", "model.layers.6.mlp.shared_experts.down_proj", "model.layers.7.attention.dense", "model.layers.7.mlp.shared_experts.gate_proj", "model.layers.7.mlp.shared_experts.up_proj", "model.layers.7.mlp.shared_experts.down_proj", "model.layers.8.attention.dense", "model.layers.8.mlp.shared_experts.gate_proj", "model.layers.8.mlp.shared_experts.up_proj", "model.layers.8.mlp.shared_experts.down_proj", "model.layers.9.attention.dense", "model.layers.9.mlp.shared_experts.gate_proj", "model.layers.9.mlp.shared_experts.up_proj", "model.layers.9.mlp.shared_experts.down_proj", "model.layers.10.attention.dense", "model.layers.10.mlp.shared_experts.gate_proj", "model.layers.10.mlp.shared_experts.up_proj", "model.layers.10.mlp.shared_experts.down_proj", "model.layers.11.attention.dense", "model.layers.11.mlp.shared_experts.gate_proj", "model.layers.11.mlp.shared_experts.up_proj", "model.layers.11.mlp.shared_experts.down_proj", "model.layers.12.attention.dense", "model.layers.12.mlp.shared_experts.gate_proj", "model.layers.12.mlp.shared_experts.up_proj", "model.layers.12.mlp.shared_experts.down_proj", "model.layers.13.attention.dense", "model.layers.13.mlp.shared_experts.gate_proj", "model.layers.13.mlp.shared_experts.up_proj", "model.layers.13.mlp.shared_experts.down_proj", "model.layers.14.attention.dense", "model.layers.14.mlp.shared_experts.gate_proj", "model.layers.14.mlp.shared_experts.up_proj", "model.layers.14.mlp.shared_experts.down_proj", "model.layers.15.attention.dense", "model.layers.15.mlp.shared_experts.gate_proj", "model.layers.15.mlp.shared_experts.up_proj", "model.layers.15.mlp.shared_experts.down_proj", "model.layers.16.attention.dense", "model.layers.16.mlp.shared_experts.gate_proj", "model.layers.16.mlp.shared_experts.up_proj", "model.layers.16.mlp.shared_experts.down_proj", "model.layers.17.attention.dense", "model.layers.17.mlp.shared_experts.gate_proj", "model.layers.17.mlp.shared_experts.up_proj", "model.layers.17.mlp.shared_experts.down_proj", "model.layers.18.attention.dense", "model.layers.18.mlp.shared_experts.gate_proj", "model.layers.18.mlp.shared_experts.up_proj", "model.layers.18.mlp.shared_experts.down_proj", "model.layers.19.attention.dense", "model.layers.19.mlp.shared_experts.gate_proj", "model.layers.19.mlp.shared_experts.up_proj", "model.layers.19.mlp.shared_experts.down_proj", "model.layers.20.attention.dense", "model.layers.20.mlp.shared_experts.gate_proj", "model.layers.20.mlp.shared_experts.up_proj", "model.layers.20.mlp.shared_experts.down_proj", "model.layers.21.attention.dense", "model.layers.21.mlp.shared_experts.gate_proj", "model.layers.21.mlp.shared_experts.up_proj", "model.layers.21.mlp.shared_experts.down_proj", "model.layers.22.attention.dense", "model.layers.22.mlp.shared_experts.gate_proj", "model.layers.22.mlp.shared_experts.up_proj", "model.layers.22.mlp.shared_experts.down_proj", "model.layers.23.attention.dense", "model.layers.23.mlp.shared_experts.gate_proj", "model.layers.23.mlp.shared_experts.up_proj", "model.layers.23.mlp.shared_experts.down_proj", "model.layers.24.attention.dense", "model.layers.24.mlp.shared_experts.gate_proj", "model.layers.24.mlp.shared_experts.up_proj", "model.layers.24.mlp.shared_experts.down_proj", "model.layers.25.attention.dense", "model.layers.25.mlp.shared_experts.gate_proj", "model.layers.25.mlp.shared_experts.up_proj", "model.layers.25.mlp.shared_experts.down_proj", "model.layers.26.attention.dense", "model.layers.26.mlp.shared_experts.gate_proj", "model.layers.26.mlp.shared_experts.up_proj", "model.layers.26.mlp.shared_experts.down_proj", "model.layers.27.attention.dense", "model.layers.27.mlp.shared_experts.gate_proj", "model.layers.27.mlp.shared_experts.up_proj", "model.layers.27.mlp.shared_experts.down_proj", "model.layers.28.attention.dense", "model.layers.28.mlp.shared_experts.gate_proj", "model.layers.28.mlp.shared_experts.up_proj", "model.layers.28.mlp.shared_experts.down_proj", "model.layers.29.attention.dense", "model.layers.29.mlp.shared_experts.gate_proj", "model.layers.29.mlp.shared_experts.up_proj", "model.layers.29.mlp.shared_experts.down_proj", "model.layers.30.attention.dense", "model.layers.30.mlp.shared_experts.gate_proj", "model.layers.30.mlp.shared_experts.up_proj", "model.layers.30.mlp.shared_experts.down_proj", "model.layers.31.attention.dense", "model.layers.31.mlp.shared_experts.gate_proj", "model.layers.31.mlp.shared_experts.up_proj", "model.layers.31.mlp.shared_experts.down_proj", "lm_head" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": {}, "transform_config": {}, "version": "0.11.1.a20250912" }, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 600000, "routed_scaling_factor": 2.5, "router_dtype": "fp32", "score_function": "sigmoid", "tie_word_embeddings": false, "topk_group": 4, "transformers_version": "4.57.0.dev0", "use_bias": false, "use_cache": true, "use_qk_norm": true, "use_qkv_bias": false, "use_rmsnorm": true, "vocab_size": 157184 }