{ "_name_or_path": "roberta-base", "activation_dropout": 0.0, "activation_function": "gelu", "architectures": [ "BartForSequenceClassification" ], "attention_dropout": 0.0, "attention_probs_dropout_prob": 0.1, "bos_token_id": 0, "classifier_dropout": 0.0, "d_model": 768, "decoder_attention_heads": 16, "decoder_ffn_dim": 4096, "decoder_layerdrop": 0.0, "decoder_layers": 12, "decoder_start_token_id": 2, "dropout": 0.1, "encoder_attention_heads": 12, "encoder_ffn_dim": 4096, "encoder_layerdrop": 0.0, "encoder_layers": 12, "eos_token_id": 2, "forced_eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "init_std": 0.02, "initializer_range": 0.02, "intermediate_size": 3072, "is_encoder_decoder": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_type": "bart", "num_hidden_layers": 12, "pad_token_id": 1, "problem_type": "single_label_classification", "scale_embedding": false, "torch_dtype": "float32", "transformers_version": "4.36.1", "type_vocab_size": 1, "use_cache": true, "vocab_size": 50265 }