| { |
| "_attn_implementation": "eager", |
| "architectures": [ |
| "Ernie4_5_MoeForCausalLM" |
| ], |
| "attention_probs_dropout_prob": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_ernie4_5_moe.Ernie4_5_MoeConfig", |
| "AutoModel": "modeling_ernie4_5_moe.Ernie4_5_Model", |
| "AutoModelForCausalLM": "modeling_ernie4_5_moe.Ernie4_5_MoeForCausalLM" |
| }, |
| "bos_token_id": 1, |
| "enable_mtp_magic_send": false, |
| "eos_token_id": 2, |
| "head_dim": 128, |
| "hidden_act": "silu", |
| "hidden_dropout_prob": 0.0, |
| "hidden_size": 1024, |
| "ignored_index": -100, |
| "initializer_range": 0.018041293779826325, |
| "intermediate_size": 3072, |
| "max_position_embeddings": 131072, |
| "model_type": "ernie4_5_moe", |
| "moe_capacity": [], |
| "moe_dense_experts_token_type_id": 3, |
| "moe_gate": "topk", |
| "moe_gate_act": "softmax", |
| "moe_group_experts": false, |
| "moe_intermediate_size": 0, |
| "moe_k": 2, |
| "moe_layer_end_index": 17, |
| "moe_layer_interval": 2, |
| "moe_layer_start_index": 0, |
| "moe_norm_gate_logits": true, |
| "moe_num_experts": null, |
| "moe_num_shared_experts": 0, |
| "moe_reverse_token_drop": false, |
| "moe_use_aux_free": false, |
| "moe_use_hard_gate": false, |
| "multi_token_pred_lambda": 0.3, |
| "num_attention_heads": 16, |
| "num_hidden_layers": 18, |
| "num_key_value_heads": 2, |
| "num_nextn_predict_layers": 0, |
| "pad_token_id": 0, |
| "paddleformers_version": "0.1", |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 500000, |
| "sinkhorn_2gate": true, |
| "sinkhorn_temp": 0.03, |
| "tensor_parallel_degree": -1, |
| "tie_word_embeddings": true, |
| "token_balance_loss": false, |
| "token_balance_seqlen": false, |
| "torch_dtype": "bfloat16", |
| "use_bias": false, |
| "use_cache": true, |
| "use_recompute_mtp": false, |
| "vocab_size": 103424, |
| "weight_share_add_bias": true |
| } |
