{ "add_router_probs": false, "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" }, "draft_config": null, "dtype": "bfloat16", "embedding_dropout": 0.0, "eos_token_id": 156892, "first_k_dense_replace": 1, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.006, "intermediate_size": 9216, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "bailing_moe_v2", "moe_intermediate_size": 1024, "moe_router_enable_expert_bias": true, "mtp_loss_scaling_factor": 1.0, "n_group": 8, "n_kv_heads": 4, "n_rep": 1, "norm_head": false, "norm_softmax": false, "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_pred_heads": null, "num_shared_experts": 1, "output_dropout": 0.0, "output_router_logits": false, "pad_token_id": 156892, "partial_rotary_factor": 0.5, "pretraining_tp": 1, "quantization_config": { "config_groups": { "group_0": { "format": "pack-quantized", "input_activations": null, "output_activations": null, "targets": [ "Linear" ], "weights": { "actorder": "group", "block_structure": null, "dynamic": false, "group_size": 128, "num_bits": 4, "observer": "minmax", "observer_kwargs": {}, "strategy": "group", "symmetric": true, "type": "int" } } }, "format": "pack-quantized", "global_compression_ratio": null, "ignore": [ "lm_head" ], "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_scaling": null, "rope_theta": 600000, "rotary_dim": 64, "rotary_scaling_factor": null, "routed_scaling_factor": 2.5, "router_dtype": "fp32", "score_function": "sigmoid", "sliding_window": null, "tie_word_embeddings": false, "topk_group": 4, "transformers_version": "4.57.1", "use_bias": false, "use_cache": true, "use_qk_norm": true, "use_qkv_bias": false, "use_rmsnorm": true, "use_sliding_window": false, "using_split_qkv_in_self_attention": false, "vocab_size": 157184 }