{ | |
"_name_or_path": "tiny_models/albert/AlbertModel", | |
"architectures": [ | |
"AlbertModel" | |
], | |
"attention_probs_dropout_prob": 0.1, | |
"bos_token_id": 2, | |
"classifier_dropout_prob": 0.1, | |
"embedding_size": 128, | |
"eos_token_id": 3, | |
"hidden_act": "gelu", | |
"hidden_dropout_prob": 0.1, | |
"hidden_size": 36, | |
"initializer_range": 0.02, | |
"inner_group_num": 1, | |
"intermediate_size": 37, | |
"layer_norm_eps": 1e-12, | |
"max_position_embeddings": 512, | |
"model_type": "albert", | |
"num_attention_heads": 6, | |
"num_hidden_groups": 6, | |
"num_hidden_layers": 6, | |
"pad_token_id": 0, | |
"position_embedding_type": "absolute", | |
"torch_dtype": "float32", | |
"transformers_version": "4.28.0.dev0", | |
"type_vocab_size": 16, | |
"vocab_size": 30000 | |
} | |