|
{ |
|
"_name_or_path": "jam15/bert-finetuned-combine-p5-adapter", |
|
"adapters": { |
|
"adapters": { |
|
"classification_adapter": "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": [ |
|
"BertModelWithHeads" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"classifier_dropout": null, |
|
"gradient_checkpointing": false, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 768, |
|
"id2label": { |
|
"0": "loc1lay1", |
|
"1": "loc1lay2", |
|
"10": "loc3lay3", |
|
"11": "loc3lay4", |
|
"12": "loc4lay1", |
|
"13": "loc4lay2", |
|
"14": "loc4lay3", |
|
"15": "loc4lay4", |
|
"16": "loc5+", |
|
"17": "loc1", |
|
"18": "loc2", |
|
"19": "loc3", |
|
"2": "loc1lay3", |
|
"20": "loc4", |
|
"21": "nfw", |
|
"22": "tfw", |
|
"23": "tfwc", |
|
"24": "tfwp", |
|
"25": "fwb", |
|
"26": "lay1", |
|
"27": "lay2", |
|
"28": "lay3", |
|
"29": "lay4", |
|
"3": "loc1lay4", |
|
"4": "loc2lay1", |
|
"5": "loc2lay2", |
|
"6": "loc2lay3", |
|
"7": "loc2lay4", |
|
"8": "loc3lay1", |
|
"9": "loc3lay2" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"label2id": { |
|
"fwb": 25, |
|
"lay1": 26, |
|
"lay2": 27, |
|
"lay3": 28, |
|
"lay4": 29, |
|
"loc1": 17, |
|
"loc1lay1": 0, |
|
"loc1lay2": 1, |
|
"loc1lay3": 2, |
|
"loc1lay4": 3, |
|
"loc2": 18, |
|
"loc2lay1": 4, |
|
"loc2lay2": 5, |
|
"loc2lay3": 6, |
|
"loc2lay4": 7, |
|
"loc3": 19, |
|
"loc3lay1": 8, |
|
"loc3lay2": 9, |
|
"loc3lay3": 10, |
|
"loc3lay4": 11, |
|
"loc4": 20, |
|
"loc4lay1": 12, |
|
"loc4lay2": 13, |
|
"loc4lay3": 14, |
|
"loc4lay4": 15, |
|
"loc5+": 16, |
|
"nfw": 21, |
|
"tfw": 22, |
|
"tfwc": 23, |
|
"tfwp": 24 |
|
}, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 512, |
|
"model_type": "bert", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 12, |
|
"pad_token_id": 0, |
|
"position_embedding_type": "absolute", |
|
"prediction_heads": { |
|
"classification_adapter": { |
|
"activation_function": "tanh", |
|
"bias": true, |
|
"head_type": "classification", |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1, |
|
"LABEL_10": 10, |
|
"LABEL_11": 11, |
|
"LABEL_12": 12, |
|
"LABEL_13": 13, |
|
"LABEL_14": 14, |
|
"LABEL_15": 15, |
|
"LABEL_16": 16, |
|
"LABEL_17": 17, |
|
"LABEL_18": 18, |
|
"LABEL_19": 19, |
|
"LABEL_2": 2, |
|
"LABEL_20": 20, |
|
"LABEL_21": 21, |
|
"LABEL_22": 22, |
|
"LABEL_23": 23, |
|
"LABEL_24": 24, |
|
"LABEL_25": 25, |
|
"LABEL_26": 26, |
|
"LABEL_27": 27, |
|
"LABEL_28": 28, |
|
"LABEL_29": 29, |
|
"LABEL_3": 3, |
|
"LABEL_4": 4, |
|
"LABEL_5": 5, |
|
"LABEL_6": 6, |
|
"LABEL_7": 7, |
|
"LABEL_8": 8, |
|
"LABEL_9": 9 |
|
}, |
|
"layers": 2, |
|
"num_labels": 30, |
|
"use_pooler": false |
|
} |
|
}, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.26.1", |
|
"type_vocab_size": 2, |
|
"use_cache": true, |
|
"vocab_size": 30522 |
|
} |
|
|