| { |
| "architectures": [ |
| "MobileBertForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.2, |
| "classifier_activation": false, |
| "classifier_dropout": null, |
| "dtype": "float32", |
| "embedding_size": 128, |
| "hidden_act": "relu", |
| "hidden_dropout_prob": 0.2, |
| "hidden_size": 512, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1", |
| "2": "LABEL_2", |
| "3": "LABEL_3", |
| "4": "LABEL_4", |
| "5": "LABEL_5", |
| "6": "LABEL_6", |
| "7": "LABEL_7", |
| "8": "LABEL_8", |
| "9": "LABEL_9", |
| "10": "LABEL_10", |
| "11": "LABEL_11", |
| "12": "LABEL_12", |
| "13": "LABEL_13", |
| "14": "LABEL_14", |
| "15": "LABEL_15", |
| "16": "LABEL_16", |
| "17": "LABEL_17" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 512, |
| "intra_bottleneck_size": 128, |
| "key_query_shared_bottleneck": true, |
| "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_2": 2, |
| "LABEL_3": 3, |
| "LABEL_4": 4, |
| "LABEL_5": 5, |
| "LABEL_6": 6, |
| "LABEL_7": 7, |
| "LABEL_8": 8, |
| "LABEL_9": 9 |
| }, |
| "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, |
| "pad_token_id": 0, |
| "problem_type": "single_label_classification", |
| "tie_word_embeddings": true, |
| "transformers_version": "5.0.0", |
| "trigram_input": true, |
| "true_hidden_size": 128, |
| "type_vocab_size": 2, |
| "use_bottleneck": true, |
| "use_bottleneck_attention": false, |
| "use_cache": false, |
| "vocab_size": 30522 |
| } |
|
|
