{ "activation_dropout": 0.0, "activation_function": "gelu", "add_bias_logits": false, "add_final_layer_norm": false, "architectures": [ "BartForConditionalGeneration" ], "attention_dropout": 0.0, "bos_token_id": 0, "classifier_dropout": 0.0, "d_model": 1024, "decoder_attention_heads": 16, "decoder_ffn_dim": 4096, "decoder_layerdrop": 0, "decoder_layers": 6, "decoder_start_token_id": 2, "dropout": 0.0, "early_stopping": true, "encoder_attention_heads": 16, "encoder_ffn_dim": 4096, "encoder_layerdrop": 0, "encoder_layers": 6, "eos_token_id": 2, "forced_bos_token_id": 0, "forced_eos_token_id": 2, "gradient_checkpointing": false, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "init_std": 0.02, "is_encoder_decoder": true, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "max_position_embeddings": 2048, "model_type": "bart", "normalize_before": false, "num_beams": 5, "num_hidden_layers": 6, "pad_token_id": 1, "scale_embedding": false, "torch_dtype": "float32", "transformers_version": "4.22.2", "use_cache": true, "vocab_size": 16113 }