| { | |
| "_num_labels": 3, | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "adapters": { | |
| "adapters": { | |
| "mrw2eng": "9076f36a74755ac4" | |
| }, | |
| "config_map": { | |
| "9076f36a74755ac4": { | |
| "adapter_residual_before_ln": false, | |
| "cross_adapter": false, | |
| "dropout": 0.0, | |
| "factorized_phm_W": true, | |
| "factorized_phm_rule": false, | |
| "hypercomplex_nonlinearity": "glorot-uniform", | |
| "init_weights": "bert", | |
| "init_weights_seed": null, | |
| "inv_adapter": null, | |
| "inv_adapter_reduction_factor": null, | |
| "is_parallel": false, | |
| "learn_phm": true, | |
| "leave_out": [], | |
| "ln_after": false, | |
| "ln_before": false, | |
| "mh_adapter": false, | |
| "non_linearity": "relu", | |
| "original_ln_after": true, | |
| "original_ln_before": true, | |
| "output_adapter": true, | |
| "phm_bias": true, | |
| "phm_c_init": "normal", | |
| "phm_dim": 4, | |
| "phm_init_range": 0.0001, | |
| "phm_layer": false, | |
| "phm_rank": 1, | |
| "reduction_factor": 16, | |
| "residual_before_ln": true, | |
| "scaling": 1.0, | |
| "shared_W_phm": false, | |
| "shared_phm_rule": true, | |
| "stochastic_depth": 0.0, | |
| "use_gating": false | |
| } | |
| }, | |
| "fusion_config_map": {}, | |
| "fusion_name_map": {}, | |
| "fusions": {} | |
| }, | |
| "add_bias_logits": false, | |
| "add_final_layer_norm": true, | |
| "architectures": [ | |
| "MBartAdapterModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 0, | |
| "classif_dropout": 0.0, | |
| "classifier_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, | |
| "early_stopping": null, | |
| "encoder_attention_heads": 16, | |
| "encoder_ffn_dim": 4096, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 12, | |
| "eos_token_id": 2, | |
| "forced_eos_token_id": 2, | |
| "gradient_checkpointing": false, | |
| "id2label": null, | |
| "init_std": 0.02, | |
| "is_encoder_decoder": true, | |
| "label2id": null, | |
| "max_length": null, | |
| "max_position_embeddings": 1024, | |
| "model_type": "mbart", | |
| "normalize_before": true, | |
| "normalize_embedding": true, | |
| "num_beams": null, | |
| "num_hidden_layers": 12, | |
| "output_past": true, | |
| "pad_token_id": 1, | |
| "prediction_heads": { | |
| "default": { | |
| "activation_function": null, | |
| "bias": false, | |
| "head_type": "seq2seq_lm", | |
| "label2id": null, | |
| "layer_norm": false, | |
| "layers": 1, | |
| "shift_labels": false, | |
| "vocab_size": 250054 | |
| } | |
| }, | |
| "scale_embedding": true, | |
| "static_position_embeddings": false, | |
| "tokenizer_class": "MBart50Tokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.51.3", | |
| "use_cache": true, | |
| "vocab_size": 250054 | |
| } | |