| { | |
| "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" | |
| }, | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 156895, | |
| "first_k_dense_replace": 1, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "intermediate_size": 9216, | |
| "max_position_embeddings": 32768, | |
| "model_type": "bailing_moe", | |
| "moe_intermediate_size": 1024, | |
| "moe_router_enable_expert_bias": true, | |
| "moe_shared_expert_intermediate_size": 1024, | |
| "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_shared_experts": 1, | |
| "output_dropout": 0.0, | |
| "pad_token_id": 156892, | |
| "partial_rotary_factor": 0.5, | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine", | |
| "model.layers.1.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.2.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.3.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.4.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.5.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.6.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.7.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.8.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.9.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.10.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.11.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.12.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.13.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.14.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.15.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.16.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.17.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.18.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.19.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.20.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.21.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.22.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.23.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.24.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.25.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.26.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.27.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.28.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.29.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.30.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.31.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| } | |
| }, | |
| "quantization_config": { | |
| "group_size": 64, | |
| "bits": 6, | |
| "mode": "affine", | |
| "model.layers.1.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.2.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.3.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.4.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.5.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.6.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.7.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.8.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.9.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.10.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.11.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.12.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.13.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.14.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.15.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.16.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.17.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.18.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.19.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.20.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.21.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.22.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.23.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.24.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.25.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.26.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.27.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.28.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.29.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.30.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| }, | |
| "model.layers.31.mlp.gate.gate_proj": { | |
| "group_size": 64, | |
| "bits": 8 | |
| } | |
| }, | |
| "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, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.3", | |
| "use_bias": false, | |
| "use_cache": true, | |
| "use_qk_norm": true, | |
| "use_qkv_bias": false, | |
| "use_rmsnorm": true, | |
| "vocab_size": 157184 | |
| } |