{"architectures": ["BertForMaskedLM"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "neuron": {"compiler_version": "2.13.66.0+6dfecc895", "input_specs": {"attention_mask": [4, 256], "input_ids": [4, 256], "labels": [4], "token_type_ids": [4, 256]}, "model_class": "BertForSequenceClassification", "num_neuron_cores_per_node": 2, "pipeline_parallel_size": 1, "precision": "bfloat16", "tensor_parallel_size": 1, "training": true}, "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "position_embedding_type": "absolute", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522}