|
{ |
|
"_name_or_path": "roberta-base", |
|
"adapters": { |
|
"adapters": { |
|
"super_glue_boolq": "9076f36a74755ac4" |
|
}, |
|
"config_map": { |
|
"9076f36a74755ac4": { |
|
"adapter_residual_before_ln": false, |
|
"cross_adapter": false, |
|
"factorized_phm_W": true, |
|
"factorized_phm_rule": false, |
|
"hypercomplex_nonlinearity": "glorot-uniform", |
|
"init_weights": "bert", |
|
"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, |
|
"use_gating": false |
|
} |
|
}, |
|
"fusion_config_map": {}, |
|
"fusions": {} |
|
}, |
|
"architectures": [ |
|
"RobertaModelWithHeads" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"bos_token_id": 0, |
|
"classifier_dropout": null, |
|
"eos_token_id": 2, |
|
"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": 514, |
|
"model_type": "roberta", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 12, |
|
"pad_token_id": 1, |
|
"position_embedding_type": "absolute", |
|
"prediction_heads": { |
|
"super_glue_boolq": { |
|
"activation_function": "tanh", |
|
"bias": true, |
|
"head_type": "classification", |
|
"label2id": { |
|
"False": 0, |
|
"True": 1 |
|
}, |
|
"layers": 2, |
|
"num_labels": 2, |
|
"use_pooler": false |
|
} |
|
}, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.21.3", |
|
"type_vocab_size": 1, |
|
"use_cache": false, |
|
"vocab_size": 50265 |
|
} |
|
|