trl-internal-testing/tiny-BartModel

1{2  "activation_dropout": 0.1,3  "activation_function": "gelu",4  "add_bias_logits": false,5  "add_final_layer_norm": false,6  "architectures": [7    "BartModel"8  ],9  "attention_dropout": 0.1,10  "bos_token_id": 0,11  "classif_dropout": 0.1,12  "classifier_dropout": 0.0,13  "d_model": 24,14  "decoder_attention_heads": 12,15  "decoder_ffn_dim": 3072,16  "decoder_layerdrop": 0.0,17  "decoder_layers": 6,18  "decoder_start_token_id": 2,19  "dropout": 0.1,20  "dtype": "float32",21  "early_stopping": true,22  "encoder_attention_heads": 12,23  "encoder_ffn_dim": 3072,24  "encoder_layerdrop": 0.0,25  "encoder_layers": 6,26  "eos_token_id": 2,27  "forced_bos_token_id": 0,28  "forced_eos_token_id": 2,29  "gradient_checkpointing": false,30  "id2label": {31    "0": "LABEL_0",32    "1": "LABEL_1",33    "2": "LABEL_2"34  },35  "init_std": 0.02,36  "is_encoder_decoder": true,37  "label2id": {38    "LABEL_0": 0,39    "LABEL_1": 1,40    "LABEL_2": 241  },42  "max_position_embeddings": 1024,43  "model_type": "bart",44  "no_repeat_ngram_size": 3,45  "normalize_before": false,46  "normalize_embedding": true,47  "num_beams": 4,48  "num_hidden_layers": 6,49  "pad_token_id": 1,50  "scale_embedding": false,51  "task_specific_params": {52    "summarization": {53      "length_penalty": 1.0,54      "max_length": 128,55      "min_length": 12,56      "num_beams": 457    },58    "summarization_cnn": {59      "length_penalty": 2.0,60      "max_length": 142,61      "min_length": 56,62      "num_beams": 463    },64    "summarization_xsum": {65      "length_penalty": 1.0,66      "max_length": 62,67      "min_length": 11,68      "num_beams": 669    }70  },71  "transformers_version": "4.57.3",72  "use_cache": true,73  "vocab_size": 5026574}75