{ | |
"init_args": [ | |
{ | |
"vocab_size": 30522, | |
"embedding_size": 128, | |
"hidden_size": 256, | |
"num_hidden_layers": 12, | |
"num_attention_heads": 4, | |
"intermediate_size": 1024, | |
"hidden_act": "gelu", | |
"hidden_dropout_prob": 0.1, | |
"attention_probs_dropout_prob": 0.1, | |
"max_position_embeddings": 128, | |
"type_vocab_size": 2, | |
"initializer_range": 0.02, | |
"pad_token_id": 0, | |
"rotary_value": true, | |
"init_class": "RoFormerModel" | |
} | |
], | |
"init_class": "RoFormerForPretraining" | |
} | |