{ "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 512, "initializer_range": 0.02, "intermediate_size": 1024, "num_attention_heads": 6, "attention_head_size": 64, "num_hidden_layers": 8, "vocab_size": 50000, "relative_attention_num_buckets": 32, "attention_scale": false, "is_dropout": true, "model": "mt5.1.1", "segment_vocab_size": 0 }