| { |
| "architectures": [ |
| "EncoderDecoderModel" |
| ], |
| "decoder": { |
| "_name_or_path": "bert-base-uncased", |
| "add_cross_attention": true, |
| "architectures": [ |
| "BertForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "bos_token_id": 2, |
| "classifier_dropout": null, |
| "eos_token_id": 3, |
| "gradient_checkpointing": false, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 512, |
| "initializer_range": 0.02, |
| "intermediate_size": 1024, |
| "is_decoder": true, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 6, |
| "pad_token_id": 1, |
| "position_embedding_type": "absolute", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 1000 |
| }, |
| "decoder_start_token_id": 2, |
| "dtype": "float32", |
| "encoder": { |
| "_name_or_path": "bert-base-uncased", |
| "architectures": [ |
| "BertForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "gradient_checkpointing": false, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 512, |
| "initializer_range": 0.02, |
| "intermediate_size": 1024, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 8, |
| "num_hidden_layers": 6, |
| "position_embedding_type": "absolute", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 1000 |
| }, |
| "eos_token_id": 3, |
| "is_encoder_decoder": true, |
| "model_type": "encoder-decoder", |
| "pad_token_id": 1, |
| "transformers_version": "4.57.1", |
| "vocab_size": 1000 |
| } |
|
|
