Hugging Face's logo

xihajun
/
50_pruned_model_compiled

Question Answering
Transformers
PyTorch
bert
Model card Files
xet
 Community
1
xihajun commited on
Commit
0c06c74
路
1 Parent(s): b647b79

Upload BertForQuestionAnswering

Browse files
Files changed (2) hide show
  1. config.json +30 -102
  2. pytorch_model.bin +2 -2
config.json CHANGED
@@ -1,120 +1,48 @@
1
  {
2
- "_name_or_path": "twmkn9/bert-base-uncased-squad2",
3
  "architectures": [
4
  "BertForQuestionAnswering"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
- "hidden_size": 768,
11
  "initializer_range": 0.02,
12
- "intermediate_size": 3072,
13
  "layer_norm_eps": 1e-12,
14
  "max_position_embeddings": 512,
15
  "model_type": "bert",
16
- "num_attention_heads": 12,
17
- "num_hidden_layers": 12,
18
- "output_past": true,
19
  "pad_token_id": 0,
20
  "position_embedding_type": "absolute",
21
  "pruned_heads": {
22
- "0": [
23
- 6,
24
- 7,
25
- 8,
26
- 9,
27
- 10,
28
- 11
29
- ],
30
- "1": [
31
- 6,
32
- 7,
33
- 8,
34
- 9,
35
- 10,
36
- 11
37
- ],
38
- "2": [
39
- 6,
40
- 7,
41
- 8,
42
- 9,
43
- 10,
44
- 11
45
- ],
46
- "3": [
47
- 6,
48
- 7,
49
- 8,
50
- 9,
51
- 10,
52
- 11
53
- ],
54
- "4": [
55
- 6,
56
- 7,
57
- 8,
58
- 9,
59
- 10,
60
- 11
61
- ],
62
- "5": [
63
- 6,
64
- 7,
65
- 8,
66
- 9,
67
- 10,
68
- 11
69
- ],
70
- "6": [
71
- 6,
72
- 7,
73
- 8,
74
- 9,
75
- 10,
76
- 11
77
- ],
78
- "7": [
79
- 6,
80
- 7,
81
- 8,
82
- 9,
83
- 10,
84
- 11
85
- ],
86
- "8": [
87
- 6,
88
- 7,
89
- 8,
90
- 9,
91
- 10,
92
- 11
93
- ],
94
- "9": [
95
- 6,
96
- 7,
97
- 8,
98
- 9,
99
- 10,
100
- 11
101
- ],
102
- "10": [
103
- 6,
104
- 7,
105
- 8,
106
- 9,
107
- 10,
108
- 11
109
- ],
110
- "11": [
111
- 6,
112
- 7,
113
- 8,
114
- 9,
115
- 10,
116
- 11
117
- ]
118
  },
119
  "torch_dtype": "float32",
120
  "transformers_version": "4.33.1",
 
1
  {
2
+ "_name_or_path": "50_pruned_model_test",
3
  "architectures": [
4
  "BertForQuestionAnswering"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
7
  "classifier_dropout": null,
8
+ "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
  "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
  "layer_norm_eps": 1e-12,
15
  "max_position_embeddings": 512,
16
  "model_type": "bert",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
 
19
  "pad_token_id": 0,
20
  "position_embedding_type": "absolute",
21
  "pruned_heads": {
22
+ "0": [],
23
+ "1": [],
24
+ "2": [],
25
+ "3": [],
26
+ "4": [],
27
+ "5": [],
28
+ "6": [],
29
+ "7": [],
30
+ "8": [],
31
+ "9": [],
32
+ "10": [],
33
+ "11": [],
34
+ "12": [],
35
+ "13": [],
36
+ "14": [],
37
+ "15": [],
38
+ "16": [],
39
+ "17": [],
40
+ "18": [],
41
+ "19": [],
42
+ "20": [],
43
+ "21": [],
44
+ "22": [],
45
+ "23": []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  },
47
  "torch_dtype": "float32",
48
  "transformers_version": "4.33.1",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47f20426c09472023daac5296dfd8be87990d1f68a4da4be6d48872244a01cbf
3
- size 378960041
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:943f6eef6675485fbf05be5aa005be5c40b10351dff1f6141b11771329dd1c0a
3
+ size 1336505641