{ "architectures": [ "StructRoberta", "StructRobertaForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "auto_map": { "AutoConfig": "modeling_structroberta.StructRobertaConfig", "AutoModelForMaskedLM": "modeling_structroberta.StructRoberta", "AutoModelForSequenceClassification": "modeling_structroberta.StructRobertaForSequenceClassification" }, "bos_token_id": 0, "classifier_dropout": null, "conv_size": 9, "eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_type": "roberta", "n_cntxt_layers": 4, "n_cntxt_layers_2": 0, "n_parser_layers": 6, "num_attention_heads": 12, "num_hidden_layers": 8, "pad_token_id": 1, "position_embedding_type": "absolute", "relations": [ "head", "child" ], "torch_dtype": "float32", "transformers_version": "4.18.0", "type_vocab_size": 1, "use_cache": true, "vocab_size": 32000, "weight_act": "softmax" }