|
{ |
|
"_name_or_path": "madlag/bert-large-uncased-wwm-squadv2-x2.63-f82.6-d16-hybrid-v1", |
|
"architectures": [ |
|
"BertForQuestionAnswering" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"classifier_dropout": null, |
|
"gradient_checkpointing": false, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 1024, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 4096, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 512, |
|
"num_attention_heads": 16, |
|
"num_hidden_layers": 24, |
|
"pad_token_id": 0, |
|
"position_embedding_type": "absolute", |
|
"pruned_heads": { |
|
"0": [ |
|
0, |
|
1, |
|
3, |
|
4, |
|
5, |
|
8, |
|
9, |
|
13, |
|
15 |
|
], |
|
"1": [ |
|
0, |
|
1, |
|
3, |
|
5, |
|
7, |
|
9, |
|
10, |
|
13, |
|
14 |
|
], |
|
"2": [ |
|
0, |
|
1, |
|
4, |
|
6, |
|
7, |
|
8, |
|
9, |
|
10, |
|
11, |
|
12, |
|
13, |
|
14, |
|
15 |
|
], |
|
"3": [ |
|
0, |
|
3, |
|
5, |
|
6, |
|
7, |
|
8, |
|
9, |
|
11, |
|
13, |
|
14, |
|
15 |
|
], |
|
"4": [ |
|
0, |
|
2, |
|
3, |
|
4, |
|
5, |
|
6, |
|
7, |
|
9, |
|
10, |
|
11, |
|
12, |
|
14 |
|
], |
|
"5": [ |
|
1, |
|
3, |
|
4, |
|
5, |
|
6, |
|
7, |
|
8, |
|
9, |
|
12, |
|
13, |
|
14, |
|
15 |
|
], |
|
"6": [ |
|
0, |
|
1, |
|
2, |
|
3, |
|
4, |
|
7, |
|
8, |
|
9, |
|
10, |
|
11, |
|
12, |
|
15 |
|
], |
|
"7": [ |
|
0, |
|
3, |
|
4, |
|
5, |
|
8, |
|
9, |
|
10, |
|
11, |
|
12, |
|
13, |
|
14 |
|
], |
|
"8": [ |
|
3, |
|
4, |
|
5, |
|
7, |
|
8, |
|
9, |
|
10, |
|
11, |
|
12 |
|
], |
|
"9": [ |
|
0, |
|
1, |
|
2, |
|
3, |
|
5, |
|
6, |
|
7, |
|
9, |
|
10, |
|
13, |
|
14, |
|
15 |
|
], |
|
"10": [ |
|
1, |
|
2, |
|
4, |
|
5, |
|
6, |
|
8, |
|
11, |
|
13 |
|
], |
|
"11": [ |
|
0, |
|
2, |
|
5, |
|
6, |
|
7, |
|
8, |
|
10, |
|
12, |
|
15 |
|
], |
|
"12": [ |
|
0, |
|
2, |
|
6, |
|
8, |
|
9, |
|
11, |
|
13 |
|
], |
|
"13": [ |
|
2, |
|
6, |
|
10, |
|
12, |
|
15 |
|
], |
|
"14": [ |
|
1, |
|
5, |
|
6, |
|
10, |
|
11, |
|
15 |
|
], |
|
"15": [ |
|
0, |
|
9 |
|
], |
|
"16": [ |
|
5, |
|
7 |
|
], |
|
"17": [ |
|
1, |
|
4, |
|
8, |
|
12, |
|
14 |
|
], |
|
"18": [ |
|
3, |
|
4, |
|
11 |
|
], |
|
"19": [ |
|
0, |
|
5, |
|
12 |
|
], |
|
"20": [ |
|
0, |
|
4, |
|
10, |
|
12 |
|
], |
|
"21": [ |
|
0, |
|
2, |
|
3, |
|
4, |
|
8, |
|
11, |
|
12, |
|
15 |
|
], |
|
"22": [ |
|
0, |
|
1, |
|
3, |
|
4, |
|
7, |
|
9, |
|
10, |
|
11, |
|
13, |
|
15 |
|
], |
|
"23": [ |
|
2, |
|
4, |
|
8, |
|
9, |
|
10, |
|
13, |
|
14, |
|
15 |
|
] |
|
}, |
|
"transformers_version": "4.24.0", |
|
"type_vocab_size": 2, |
|
"use_cache": false, |
|
"vocab_size": 30522 |
|
} |
|
|