| { |
| "architectures": [ |
| "EncoderDecoderModel" |
| ], |
| "decoder": { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "vinai/phobert-base-v2", |
| "add_cross_attention": true, |
| "architectures": [ |
| "RobertaForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "is_decoder": true, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 258, |
| "model_type": "roberta", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "position_embedding_type": "absolute", |
| "tokenizer_class": "PhobertTokenizer", |
| "torch_dtype": "float32", |
| "type_vocab_size": 1, |
| "use_cache": true, |
| "vocab_size": 64001 |
| }, |
| "decoder_start_token_id": 0, |
| "early_stopping": null, |
| "encoder": { |
| "_attn_implementation_autoset": true, |
| "_name_or_path": "vinai/phobert-base-v2", |
| "architectures": [ |
| "RobertaForMaskedLM" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 258, |
| "model_type": "roberta", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "position_embedding_type": "absolute", |
| "tokenizer_class": "PhobertTokenizer", |
| "torch_dtype": "float32", |
| "type_vocab_size": 1, |
| "use_cache": true, |
| "vocab_size": 64001 |
| }, |
| "eos_token_id": 2, |
| "is_encoder_decoder": true, |
| "length_penalty": null, |
| "max_length": null, |
| "model_type": "encoder-decoder", |
| "no_repeat_ngram_size": null, |
| "num_beams": null, |
| "pad_token_id": 2, |
| "tie_encoder_decoder": true, |
| "torch_dtype": "float32", |
| "transformers_version": "4.51.3", |
| "vocab_size": 64001 |
| } |
|
|
