| { | |
| "activation_function": "gelu_new", | |
| "attention_dropout_prob": 0.1, | |
| "embedding_dropout_prob": 0.1, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "hidden_size": 2048, | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 2048, | |
| "residual_dropout_prob": 0.1, | |
| "vocab_size": 49154 | |
| } |