| { | |
| "activation_dropout": 0.1, | |
| "activation_function": "gelu", | |
| "architectures": [ | |
| "ProphetNetForConditionalGeneration" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 102, | |
| "decoder_ffn_dim": 4096, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_max_position_embeddings": 514, | |
| "decoder_start_token_id": 102, | |
| "disable_ngram_loss": false, | |
| "dropout": 0.1, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_max_position_embeddings": 513, | |
| "eos_token_id": 102, | |
| "eps": 0.0, | |
| "gradient_checkpointing": true, | |
| "hidden_size": 1024, | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "max_position_embeddings": 513, | |
| "model_type": "prophetnet", | |
| "ngram": 2, | |
| "num_buckets": 32, | |
| "num_decoder_attention_heads": 16, | |
| "num_decoder_layers": 12, | |
| "num_encoder_attention_heads": 16, | |
| "num_encoder_layers": 12, | |
| "output_past": false, | |
| "pad_token_id": 0, | |
| "relative_max_distance": 128, | |
| "vocab_size": 9360 | |
| } | |