| { | |
| "architectures": [ | |
| "MobileBertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_activation": true, | |
| "classifier_dropout": null, | |
| "embedding_size": 64, | |
| "hidden_act": "relu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 96, | |
| "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" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 96, | |
| "intra_bottleneck_size": 96, | |
| "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_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_embedding": 96, | |
| "max_position_embeddings": 512, | |
| "model_type": "mobilebert", | |
| "normalization_type": "no_norm", | |
| "num_attention_heads": 4, | |
| "num_feedforward_networks": 6, | |
| "num_hidden_layers": 3, | |
| "pad_token_id": 0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.26.1", | |
| "trigram_input": true, | |
| "true_hidden_size": 96, | |
| "type_vocab_size": 2, | |
| "use_bottleneck": true, | |
| "use_bottleneck_attention": false, | |
| "vocab_size": 30522 | |
| } | |