{ | |
"architectures": [ | |
"LTGBertForMaskedLM" | |
], | |
"attention_probs_dropout_prob": 0.1, | |
"hidden_dropout_prob": 0.1, | |
"hidden_size": 768, | |
"initializer_range": 0.02, | |
"intermediate_size": 2048, | |
"layer_norm_eps": 1e-07, | |
"max_position_embeddings": 512, | |
"num_attention_heads": 12, | |
"num_hidden_layers": 12, | |
"output_all_encoded_layers": true, | |
"position_bucket_size": 32, | |
"torch_dtype": "float32", | |
"transformers_version": "4.26.0", | |
"vocab_size": 16384 | |
} | |