{ | |
"_name_or_path": "madlag/bert-base-uncased-squad1.1-block-sparse-0.20-v1", | |
"architectures": [ | |
"BertForQuestionAnswering" | |
], | |
"attention_probs_dropout_prob": 0.1, | |
"block_size": [ | |
32, | |
32 | |
], | |
"hidden_act": "gelu", | |
"hidden_size": 768, | |
"max_position_embeddings": 512, | |
"model_type": "bert", | |
"num_attention_heads": 12, | |
"num_hidden_layers": 12, | |
"pad_token_id": 0, | |
"pruned_heads": { | |
"0": [ | |
0, | |
2, | |
4, | |
5, | |
6, | |
7, | |
9, | |
11 | |
], | |
"1": [ | |
0, | |
1, | |
2, | |
3, | |
5, | |
6, | |
7, | |
8, | |
9 | |
], | |
"2": [ | |
1, | |
2, | |
3, | |
4, | |
5, | |
7, | |
8, | |
11 | |
], | |
"3": [ | |
2, | |
3, | |
4, | |
6, | |
7, | |
10 | |
], | |
"4": [ | |
0, | |
1, | |
2, | |
6, | |
7, | |
8, | |
10, | |
11 | |
], | |
"5": [ | |
0, | |
1, | |
2, | |
4, | |
5, | |
6, | |
7, | |
11 | |
], | |
"6": [ | |
0, | |
2, | |
3, | |
4, | |
6, | |
7, | |
10 | |
], | |
"7": [ | |
1, | |
3, | |
6, | |
7, | |
11 | |
], | |
"8": [ | |
0, | |
2, | |
3, | |
4, | |
5, | |
6, | |
7, | |
8 | |
], | |
"9": [ | |
1, | |
3, | |
4, | |
5, | |
7, | |
9, | |
10 | |
], | |
"10": [ | |
1, | |
4, | |
5, | |
6, | |
7, | |
8, | |
9 | |
], | |
"11": [ | |
0, | |
2, | |
3, | |
5, | |
6, | |
7, | |
8, | |
10, | |
11 | |
] | |
}, | |
"type_vocab_size": 2, | |
"vocab_size": 30522 | |
} | |