| {"architectures": ["ElectraForPreTraining"], "attention_probs_dropout_prob": 0.1, "embedding_size": 128, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 256, "initializer_range": 0.02, "intermediate_size": 1024, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "electra", "num_attention_heads": 4, "num_hidden_layers": 12, "pad_token_id": 0, "type_vocab_size": 2, "vocab_size": 32200} |