{ "_name_or_path": "../convert_models/albert_xxlarge_spanish/converted", "architectures": [ "AlbertForPreTraining" ], "attention_probs_dropout_prob": 0, "bos_token_id": 2, "classifier_dropout_prob": 0.1, "down_scale_factor": 1, "embedding_size": 128, "eos_token_id": 3, "gap_size": 0, "hidden_act": "gelu", "hidden_dropout_prob": 0, "hidden_size": 4096, "initializer_range": 0.01, "inner_group_num": 1, "intermediate_size": 16384, "layer_norm_eps": 1e-12, "layers_to_keep": [], "max_position_embeddings": 512, "model_type": "albert", "net_structure_type": 0, "num_attention_heads": 64, "num_hidden_groups": 1, "num_hidden_layers": 12, "num_memory_blocks": 0, "pad_token_id": 0, "position_embedding_type": "absolute", "transformers_version": "4.8.2", "type_vocab_size": 2, "vocab_size": 31000 }