{ "architectures": [ "ErnieForMaskedLM" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-05, "max_position_embeddings": 2048, "model_type": "ernie", "num_attention_heads": 16, "num_hidden_layers": 20, "pad_token_id": 0, "position_embedding_type": "absolute", "task_type_vocab_size": 16, "transformers_version": "4.29.2", "type_vocab_size": 4, "use_cache": true, "use_task_id": true, "vocab_size": 40000 }