| { | |
| "_num_labels": 3, | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "add_bias_logits": false, | |
| "add_final_layer_norm": false, | |
| "architectures": [ | |
| "BartForSequenceClassification" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "classif_dropout": 0.0, | |
| "d_model": 1024, | |
| "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": 16, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 12, | |
| "eos_token_id": 2, | |
| "finetuning_task": "qnli", | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "max_position_embeddings": 1024, | |
| "model_type": "bart", | |
| "normalize_before": false, | |
| "normalize_embedding": true, | |
| "num_hidden_layers": 12, | |
| "output_past": false, | |
| "pad_token_id": 1, | |
| "prefix": " ", | |
| "scale_embedding": false, | |
| "static_position_embeddings": false, | |
| "task_specific_params": { | |
| "summarization": { | |
| "early_stopping": true, | |
| "length_penalty": 2.0, | |
| "max_length": 142, | |
| "min_length": 56, | |
| "no_repeat_ngram_size": 3, | |
| "num_beams": 4 | |
| } | |
| }, | |
| "vocab_size": 50265 | |
| } | |