|
{ |
|
"_name_or_path": "output_stsb", |
|
"architectures": [ |
|
"MobileBertForSequenceClassification" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"classifier_activation": false, |
|
"classifier_dropout": null, |
|
"embedding_size": 128, |
|
"finetuning_task": "sts-b", |
|
"hidden_act": "relu", |
|
"hidden_dropout_prob": 0.0, |
|
"hidden_size": 512, |
|
"id2label": { |
|
"0": "LABEL_0" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 512, |
|
"intra_bottleneck_size": 128, |
|
"key_query_shared_bottleneck": true, |
|
"label2id": { |
|
"LABEL_0": 0 |
|
}, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 512, |
|
"model_type": "mobilebert", |
|
"normalization_type": "no_norm", |
|
"num_attention_heads": 4, |
|
"num_feedforward_networks": 4, |
|
"num_hidden_layers": 24, |
|
"output_hidden_states": true, |
|
"pad_token_id": 0, |
|
"problem_type": "regression", |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.20.0.dev0", |
|
"trigram_input": true, |
|
"true_hidden_size": 128, |
|
"type_vocab_size": 2, |
|
"use_bottleneck": true, |
|
"use_bottleneck_attention": false, |
|
"vocab_size": 30522 |
|
} |
|
|