| { | |
| "architectures": [ | |
| "AlbertForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0, | |
| "bos_token_id": 2, | |
| "classifier_dropout_prob": 0.1, | |
| "down_scale_factor": 1, | |
| "embedding_size": 128, | |
| "eos_token_id": 3, | |
| "finetuning_task": "ag_news", | |
| "gap_size": 0, | |
| "hidden_act": "gelu_new", | |
| "hidden_dropout_prob": 0, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2", | |
| "3": "LABEL_3" | |
| }, | |
| "initializer_range": 0.02, | |
| "inner_group_num": 1, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2, | |
| "LABEL_3": 3 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "albert", | |
| "net_structure_type": 0, | |
| "num_attention_heads": 12, | |
| "num_hidden_groups": 1, | |
| "num_hidden_layers": 12, | |
| "num_memory_blocks": 0, | |
| "pad_token_id": 0, | |
| "type_vocab_size": 2, | |
| "vocab_size": 30000 | |
| } | |