Hugging Face's logo

vuiseng9
/
bert-base-squadv1

Question Answering
Transformers
PyTorch
ONNX
bert
Model card Files
xet
Community
1
Chua, Vui Seng commited on
Commit
d96569c
路
1 Parent(s): 694812a

Add collaterals

Browse files
Files changed (11) hide show
  1. .gitattributes +2 -0
  2. README.md +26 -0
  3. all_results.json +5 -0
  4. bert-base-squadv1.onnx +3 -0
  5. eval_nbest_predictions.json +3 -0
  6. eval_predictions.json +0 -0
  7. eval_results.json +5 -0
  8. layer_wise_sparsity_global_rate_0.00.csv +200 -0
  9. layer_wise_sparsity_global_rate_0.00.md +201 -0
  10. linear_layer_sparsity_85M_params_0.00_sparsity.csv +73 -0
  11. linear_layer_sparsity_85M_params_0.00_sparsity.md +74 -0
.gitattributes CHANGED
@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ bert-base-squadv1.onnx filter=lfs diff=lfs merge=lfs -text
29
+ eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ This model is a fork of [```csarron/bert-base-uncased-squad-v1```](https://huggingface.co/csarron/bert-base-uncased-squad-v1).
2
+
3
+ ```
4
+ eval_exact_match = 80.9082
5
+ eval_f1 = 88.2275
6
+ eval_samples = 10784
7
+ ```
8
+
9
+ # Eval
10
+ ```bash
11
+ export CUDA_VISIBLE_DEVICES=0
12
+
13
+ OUTDIR=eval-bert-base-squadv1
14
+ WORKDIR=transformers/examples/pytorch/question-answering
15
+ cd $WORKDIR
16
+
17
+ nohup python run_qa.py \
18
+ --model_name_or_path vuiseng9/bert-base-squadv1 \
19
+ --dataset_name squad \
20
+ --do_eval \
21
+ --per_device_eval_batch_size 128 \
22
+ --max_seq_length 384 \
23
+ --doc_stride 128 \
24
+ --overwrite_output_dir \
25
+ --output_dir $OUTDIR 2>&1 | tee $OUTDIR/run.log &
26
+ ```
all_results.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eval_exact_match": 80.90823084200568,
3
+ "eval_f1": 88.22754061399627,
4
+ "eval_samples": 10784
5
+ }
bert-base-squadv1.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95dc1f18387c59847a7d4e63b18ab78f87ec3e04d6c65f6c492d9bba9681622e
3
+ size 435644640
eval_nbest_predictions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d30c9ccf3e7b843265ac27aa7189c8a5ac89af1e8dfc8fd7bbcfa3c9f7a83979
3
+ size 49496690
eval_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_results.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eval_exact_match": 80.90823084200568,
3
+ "eval_f1": 88.22754061399627,
4
+ "eval_samples": 10784
5
+ }
layer_wise_sparsity_global_rate_0.00.csv ADDED
@@ -0,0 +1,200 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ,layer_id,layer_type,param_type,shape,nparam,nnz,sparsity
2
+ 0,bert.embeddings.word_embeddings,Embedding,weight,"[30522, 768]",23440896,23440896,0.0
3
+ 1,bert.embeddings.position_embeddings,Embedding,weight,"[512, 768]",393216,393216,0.0
4
+ 2,bert.embeddings.token_type_embeddings,Embedding,weight,"[2, 768]",1536,1536,0.0
5
+ 3,bert.embeddings.LayerNorm,LayerNorm,weight,[768],768,768,0.0
6
+ 4,bert.embeddings.LayerNorm,LayerNorm,bias,[768],768,768,0.0
7
+ 5,bert.encoder.layer.0.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
8
+ 6,bert.encoder.layer.0.attention.self.query,Linear,bias,[768],768,768,0.0
9
+ 7,bert.encoder.layer.0.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
10
+ 8,bert.encoder.layer.0.attention.self.key,Linear,bias,[768],768,768,0.0
11
+ 9,bert.encoder.layer.0.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
12
+ 10,bert.encoder.layer.0.attention.self.value,Linear,bias,[768],768,768,0.0
13
+ 11,bert.encoder.layer.0.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
14
+ 12,bert.encoder.layer.0.attention.output.dense,Linear,bias,[768],768,768,0.0
15
+ 13,bert.encoder.layer.0.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
16
+ 14,bert.encoder.layer.0.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
17
+ 15,bert.encoder.layer.0.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
18
+ 16,bert.encoder.layer.0.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
19
+ 17,bert.encoder.layer.0.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
20
+ 18,bert.encoder.layer.0.output.dense,Linear,bias,[768],768,768,0.0
21
+ 19,bert.encoder.layer.0.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
22
+ 20,bert.encoder.layer.0.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
23
+ 21,bert.encoder.layer.1.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
24
+ 22,bert.encoder.layer.1.attention.self.query,Linear,bias,[768],768,768,0.0
25
+ 23,bert.encoder.layer.1.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
26
+ 24,bert.encoder.layer.1.attention.self.key,Linear,bias,[768],768,768,0.0
27
+ 25,bert.encoder.layer.1.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
28
+ 26,bert.encoder.layer.1.attention.self.value,Linear,bias,[768],768,768,0.0
29
+ 27,bert.encoder.layer.1.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
30
+ 28,bert.encoder.layer.1.attention.output.dense,Linear,bias,[768],768,768,0.0
31
+ 29,bert.encoder.layer.1.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
32
+ 30,bert.encoder.layer.1.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
33
+ 31,bert.encoder.layer.1.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
34
+ 32,bert.encoder.layer.1.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
35
+ 33,bert.encoder.layer.1.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
36
+ 34,bert.encoder.layer.1.output.dense,Linear,bias,[768],768,768,0.0
37
+ 35,bert.encoder.layer.1.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
38
+ 36,bert.encoder.layer.1.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
39
+ 37,bert.encoder.layer.2.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
40
+ 38,bert.encoder.layer.2.attention.self.query,Linear,bias,[768],768,768,0.0
41
+ 39,bert.encoder.layer.2.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
42
+ 40,bert.encoder.layer.2.attention.self.key,Linear,bias,[768],768,768,0.0
43
+ 41,bert.encoder.layer.2.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
44
+ 42,bert.encoder.layer.2.attention.self.value,Linear,bias,[768],768,768,0.0
45
+ 43,bert.encoder.layer.2.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
46
+ 44,bert.encoder.layer.2.attention.output.dense,Linear,bias,[768],768,768,0.0
47
+ 45,bert.encoder.layer.2.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
48
+ 46,bert.encoder.layer.2.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
49
+ 47,bert.encoder.layer.2.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
50
+ 48,bert.encoder.layer.2.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
51
+ 49,bert.encoder.layer.2.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
52
+ 50,bert.encoder.layer.2.output.dense,Linear,bias,[768],768,768,0.0
53
+ 51,bert.encoder.layer.2.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
54
+ 52,bert.encoder.layer.2.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
55
+ 53,bert.encoder.layer.3.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
56
+ 54,bert.encoder.layer.3.attention.self.query,Linear,bias,[768],768,768,0.0
57
+ 55,bert.encoder.layer.3.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
58
+ 56,bert.encoder.layer.3.attention.self.key,Linear,bias,[768],768,768,0.0
59
+ 57,bert.encoder.layer.3.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
60
+ 58,bert.encoder.layer.3.attention.self.value,Linear,bias,[768],768,768,0.0
61
+ 59,bert.encoder.layer.3.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
62
+ 60,bert.encoder.layer.3.attention.output.dense,Linear,bias,[768],768,768,0.0
63
+ 61,bert.encoder.layer.3.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
64
+ 62,bert.encoder.layer.3.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
65
+ 63,bert.encoder.layer.3.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
66
+ 64,bert.encoder.layer.3.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
67
+ 65,bert.encoder.layer.3.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
68
+ 66,bert.encoder.layer.3.output.dense,Linear,bias,[768],768,768,0.0
69
+ 67,bert.encoder.layer.3.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
70
+ 68,bert.encoder.layer.3.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
71
+ 69,bert.encoder.layer.4.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
72
+ 70,bert.encoder.layer.4.attention.self.query,Linear,bias,[768],768,768,0.0
73
+ 71,bert.encoder.layer.4.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
74
+ 72,bert.encoder.layer.4.attention.self.key,Linear,bias,[768],768,768,0.0
75
+ 73,bert.encoder.layer.4.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
76
+ 74,bert.encoder.layer.4.attention.self.value,Linear,bias,[768],768,768,0.0
77
+ 75,bert.encoder.layer.4.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
78
+ 76,bert.encoder.layer.4.attention.output.dense,Linear,bias,[768],768,768,0.0
79
+ 77,bert.encoder.layer.4.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
80
+ 78,bert.encoder.layer.4.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
81
+ 79,bert.encoder.layer.4.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
82
+ 80,bert.encoder.layer.4.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
83
+ 81,bert.encoder.layer.4.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
84
+ 82,bert.encoder.layer.4.output.dense,Linear,bias,[768],768,768,0.0
85
+ 83,bert.encoder.layer.4.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
86
+ 84,bert.encoder.layer.4.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
87
+ 85,bert.encoder.layer.5.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
88
+ 86,bert.encoder.layer.5.attention.self.query,Linear,bias,[768],768,768,0.0
89
+ 87,bert.encoder.layer.5.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
90
+ 88,bert.encoder.layer.5.attention.self.key,Linear,bias,[768],768,768,0.0
91
+ 89,bert.encoder.layer.5.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
92
+ 90,bert.encoder.layer.5.attention.self.value,Linear,bias,[768],768,768,0.0
93
+ 91,bert.encoder.layer.5.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
94
+ 92,bert.encoder.layer.5.attention.output.dense,Linear,bias,[768],768,768,0.0
95
+ 93,bert.encoder.layer.5.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
96
+ 94,bert.encoder.layer.5.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
97
+ 95,bert.encoder.layer.5.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
98
+ 96,bert.encoder.layer.5.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
99
+ 97,bert.encoder.layer.5.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
100
+ 98,bert.encoder.layer.5.output.dense,Linear,bias,[768],768,768,0.0
101
+ 99,bert.encoder.layer.5.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
102
+ 100,bert.encoder.layer.5.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
103
+ 101,bert.encoder.layer.6.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
104
+ 102,bert.encoder.layer.6.attention.self.query,Linear,bias,[768],768,768,0.0
105
+ 103,bert.encoder.layer.6.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
106
+ 104,bert.encoder.layer.6.attention.self.key,Linear,bias,[768],768,768,0.0
107
+ 105,bert.encoder.layer.6.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
108
+ 106,bert.encoder.layer.6.attention.self.value,Linear,bias,[768],768,768,0.0
109
+ 107,bert.encoder.layer.6.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
110
+ 108,bert.encoder.layer.6.attention.output.dense,Linear,bias,[768],768,768,0.0
111
+ 109,bert.encoder.layer.6.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
112
+ 110,bert.encoder.layer.6.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
113
+ 111,bert.encoder.layer.6.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
114
+ 112,bert.encoder.layer.6.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
115
+ 113,bert.encoder.layer.6.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
116
+ 114,bert.encoder.layer.6.output.dense,Linear,bias,[768],768,768,0.0
117
+ 115,bert.encoder.layer.6.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
118
+ 116,bert.encoder.layer.6.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
119
+ 117,bert.encoder.layer.7.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
120
+ 118,bert.encoder.layer.7.attention.self.query,Linear,bias,[768],768,768,0.0
121
+ 119,bert.encoder.layer.7.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
122
+ 120,bert.encoder.layer.7.attention.self.key,Linear,bias,[768],768,768,0.0
123
+ 121,bert.encoder.layer.7.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
124
+ 122,bert.encoder.layer.7.attention.self.value,Linear,bias,[768],768,768,0.0
125
+ 123,bert.encoder.layer.7.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
126
+ 124,bert.encoder.layer.7.attention.output.dense,Linear,bias,[768],768,768,0.0
127
+ 125,bert.encoder.layer.7.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
128
+ 126,bert.encoder.layer.7.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
129
+ 127,bert.encoder.layer.7.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
130
+ 128,bert.encoder.layer.7.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
131
+ 129,bert.encoder.layer.7.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
132
+ 130,bert.encoder.layer.7.output.dense,Linear,bias,[768],768,768,0.0
133
+ 131,bert.encoder.layer.7.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
134
+ 132,bert.encoder.layer.7.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
135
+ 133,bert.encoder.layer.8.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
136
+ 134,bert.encoder.layer.8.attention.self.query,Linear,bias,[768],768,768,0.0
137
+ 135,bert.encoder.layer.8.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
138
+ 136,bert.encoder.layer.8.attention.self.key,Linear,bias,[768],768,768,0.0
139
+ 137,bert.encoder.layer.8.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
140
+ 138,bert.encoder.layer.8.attention.self.value,Linear,bias,[768],768,768,0.0
141
+ 139,bert.encoder.layer.8.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
142
+ 140,bert.encoder.layer.8.attention.output.dense,Linear,bias,[768],768,768,0.0
143
+ 141,bert.encoder.layer.8.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
144
+ 142,bert.encoder.layer.8.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
145
+ 143,bert.encoder.layer.8.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
146
+ 144,bert.encoder.layer.8.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
147
+ 145,bert.encoder.layer.8.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
148
+ 146,bert.encoder.layer.8.output.dense,Linear,bias,[768],768,768,0.0
149
+ 147,bert.encoder.layer.8.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
150
+ 148,bert.encoder.layer.8.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
151
+ 149,bert.encoder.layer.9.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
152
+ 150,bert.encoder.layer.9.attention.self.query,Linear,bias,[768],768,768,0.0
153
+ 151,bert.encoder.layer.9.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
154
+ 152,bert.encoder.layer.9.attention.self.key,Linear,bias,[768],768,768,0.0
155
+ 153,bert.encoder.layer.9.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
156
+ 154,bert.encoder.layer.9.attention.self.value,Linear,bias,[768],768,768,0.0
157
+ 155,bert.encoder.layer.9.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
158
+ 156,bert.encoder.layer.9.attention.output.dense,Linear,bias,[768],768,768,0.0
159
+ 157,bert.encoder.layer.9.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
160
+ 158,bert.encoder.layer.9.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
161
+ 159,bert.encoder.layer.9.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
162
+ 160,bert.encoder.layer.9.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
163
+ 161,bert.encoder.layer.9.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
164
+ 162,bert.encoder.layer.9.output.dense,Linear,bias,[768],768,768,0.0
165
+ 163,bert.encoder.layer.9.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
166
+ 164,bert.encoder.layer.9.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
167
+ 165,bert.encoder.layer.10.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
168
+ 166,bert.encoder.layer.10.attention.self.query,Linear,bias,[768],768,768,0.0
169
+ 167,bert.encoder.layer.10.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
170
+ 168,bert.encoder.layer.10.attention.self.key,Linear,bias,[768],768,768,0.0
171
+ 169,bert.encoder.layer.10.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
172
+ 170,bert.encoder.layer.10.attention.self.value,Linear,bias,[768],768,768,0.0
173
+ 171,bert.encoder.layer.10.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
174
+ 172,bert.encoder.layer.10.attention.output.dense,Linear,bias,[768],768,768,0.0
175
+ 173,bert.encoder.layer.10.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
176
+ 174,bert.encoder.layer.10.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
177
+ 175,bert.encoder.layer.10.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
178
+ 176,bert.encoder.layer.10.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
179
+ 177,bert.encoder.layer.10.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
180
+ 178,bert.encoder.layer.10.output.dense,Linear,bias,[768],768,768,0.0
181
+ 179,bert.encoder.layer.10.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
182
+ 180,bert.encoder.layer.10.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
183
+ 181,bert.encoder.layer.11.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
184
+ 182,bert.encoder.layer.11.attention.self.query,Linear,bias,[768],768,768,0.0
185
+ 183,bert.encoder.layer.11.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
186
+ 184,bert.encoder.layer.11.attention.self.key,Linear,bias,[768],768,768,0.0
187
+ 185,bert.encoder.layer.11.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
188
+ 186,bert.encoder.layer.11.attention.self.value,Linear,bias,[768],768,768,0.0
189
+ 187,bert.encoder.layer.11.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
190
+ 188,bert.encoder.layer.11.attention.output.dense,Linear,bias,[768],768,768,0.0
191
+ 189,bert.encoder.layer.11.attention.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
192
+ 190,bert.encoder.layer.11.attention.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
193
+ 191,bert.encoder.layer.11.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
194
+ 192,bert.encoder.layer.11.intermediate.dense,Linear,bias,[3072],3072,3072,0.0
195
+ 193,bert.encoder.layer.11.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
196
+ 194,bert.encoder.layer.11.output.dense,Linear,bias,[768],768,768,0.0
197
+ 195,bert.encoder.layer.11.output.LayerNorm,LayerNorm,weight,[768],768,768,0.0
198
+ 196,bert.encoder.layer.11.output.LayerNorm,LayerNorm,bias,[768],768,768,0.0
199
+ 197,qa_outputs,Linear,weight,"[2, 768]",1536,1536,0.0
200
+ 198,qa_outputs,Linear,bias,[2],2,2,0.0
layer_wise_sparsity_global_rate_0.00.md ADDED
@@ -0,0 +1,201 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | | layer_id | layer_type | param_type | shape | nparam | nnz | sparsity |
2
+ |----:|:-------------------------------------------------|:-------------|:-------------|:-------------|---------:|---------:|-----------:|
3
+ | 0 | bert.embeddings.word_embeddings | Embedding | weight | [30522, 768] | 23440896 | 23440896 | 0 |
4
+ | 1 | bert.embeddings.position_embeddings | Embedding | weight | [512, 768] | 393216 | 393216 | 0 |
5
+ | 2 | bert.embeddings.token_type_embeddings | Embedding | weight | [2, 768] | 1536 | 1536 | 0 |
6
+ | 3 | bert.embeddings.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
7
+ | 4 | bert.embeddings.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
8
+ | 5 | bert.encoder.layer.0.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
9
+ | 6 | bert.encoder.layer.0.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
10
+ | 7 | bert.encoder.layer.0.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
11
+ | 8 | bert.encoder.layer.0.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
12
+ | 9 | bert.encoder.layer.0.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
13
+ | 10 | bert.encoder.layer.0.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
14
+ | 11 | bert.encoder.layer.0.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
15
+ | 12 | bert.encoder.layer.0.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
16
+ | 13 | bert.encoder.layer.0.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
17
+ | 14 | bert.encoder.layer.0.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
18
+ | 15 | bert.encoder.layer.0.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
19
+ | 16 | bert.encoder.layer.0.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
20
+ | 17 | bert.encoder.layer.0.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
21
+ | 18 | bert.encoder.layer.0.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
22
+ | 19 | bert.encoder.layer.0.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
23
+ | 20 | bert.encoder.layer.0.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
24
+ | 21 | bert.encoder.layer.1.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
25
+ | 22 | bert.encoder.layer.1.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
26
+ | 23 | bert.encoder.layer.1.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
27
+ | 24 | bert.encoder.layer.1.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
28
+ | 25 | bert.encoder.layer.1.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
29
+ | 26 | bert.encoder.layer.1.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
30
+ | 27 | bert.encoder.layer.1.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
31
+ | 28 | bert.encoder.layer.1.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
32
+ | 29 | bert.encoder.layer.1.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
33
+ | 30 | bert.encoder.layer.1.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
34
+ | 31 | bert.encoder.layer.1.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
35
+ | 32 | bert.encoder.layer.1.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
36
+ | 33 | bert.encoder.layer.1.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
37
+ | 34 | bert.encoder.layer.1.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
38
+ | 35 | bert.encoder.layer.1.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
39
+ | 36 | bert.encoder.layer.1.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
40
+ | 37 | bert.encoder.layer.2.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
41
+ | 38 | bert.encoder.layer.2.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
42
+ | 39 | bert.encoder.layer.2.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
43
+ | 40 | bert.encoder.layer.2.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
44
+ | 41 | bert.encoder.layer.2.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
45
+ | 42 | bert.encoder.layer.2.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
46
+ | 43 | bert.encoder.layer.2.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
47
+ | 44 | bert.encoder.layer.2.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
48
+ | 45 | bert.encoder.layer.2.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
49
+ | 46 | bert.encoder.layer.2.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
50
+ | 47 | bert.encoder.layer.2.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
51
+ | 48 | bert.encoder.layer.2.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
52
+ | 49 | bert.encoder.layer.2.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
53
+ | 50 | bert.encoder.layer.2.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
54
+ | 51 | bert.encoder.layer.2.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
55
+ | 52 | bert.encoder.layer.2.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
56
+ | 53 | bert.encoder.layer.3.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
57
+ | 54 | bert.encoder.layer.3.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
58
+ | 55 | bert.encoder.layer.3.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
59
+ | 56 | bert.encoder.layer.3.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
60
+ | 57 | bert.encoder.layer.3.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
61
+ | 58 | bert.encoder.layer.3.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
62
+ | 59 | bert.encoder.layer.3.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
63
+ | 60 | bert.encoder.layer.3.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
64
+ | 61 | bert.encoder.layer.3.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
65
+ | 62 | bert.encoder.layer.3.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
66
+ | 63 | bert.encoder.layer.3.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
67
+ | 64 | bert.encoder.layer.3.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
68
+ | 65 | bert.encoder.layer.3.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
69
+ | 66 | bert.encoder.layer.3.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
70
+ | 67 | bert.encoder.layer.3.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
71
+ | 68 | bert.encoder.layer.3.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
72
+ | 69 | bert.encoder.layer.4.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
73
+ | 70 | bert.encoder.layer.4.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
74
+ | 71 | bert.encoder.layer.4.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
75
+ | 72 | bert.encoder.layer.4.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
76
+ | 73 | bert.encoder.layer.4.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
77
+ | 74 | bert.encoder.layer.4.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
78
+ | 75 | bert.encoder.layer.4.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
79
+ | 76 | bert.encoder.layer.4.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
80
+ | 77 | bert.encoder.layer.4.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
81
+ | 78 | bert.encoder.layer.4.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
82
+ | 79 | bert.encoder.layer.4.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
83
+ | 80 | bert.encoder.layer.4.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
84
+ | 81 | bert.encoder.layer.4.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
85
+ | 82 | bert.encoder.layer.4.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
86
+ | 83 | bert.encoder.layer.4.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
87
+ | 84 | bert.encoder.layer.4.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
88
+ | 85 | bert.encoder.layer.5.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
89
+ | 86 | bert.encoder.layer.5.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
90
+ | 87 | bert.encoder.layer.5.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
91
+ | 88 | bert.encoder.layer.5.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
92
+ | 89 | bert.encoder.layer.5.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
93
+ | 90 | bert.encoder.layer.5.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
94
+ | 91 | bert.encoder.layer.5.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
95
+ | 92 | bert.encoder.layer.5.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
96
+ | 93 | bert.encoder.layer.5.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
97
+ | 94 | bert.encoder.layer.5.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
98
+ | 95 | bert.encoder.layer.5.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
99
+ | 96 | bert.encoder.layer.5.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
100
+ | 97 | bert.encoder.layer.5.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
101
+ | 98 | bert.encoder.layer.5.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
102
+ | 99 | bert.encoder.layer.5.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
103
+ | 100 | bert.encoder.layer.5.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
104
+ | 101 | bert.encoder.layer.6.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
105
+ | 102 | bert.encoder.layer.6.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
106
+ | 103 | bert.encoder.layer.6.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
107
+ | 104 | bert.encoder.layer.6.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
108
+ | 105 | bert.encoder.layer.6.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
109
+ | 106 | bert.encoder.layer.6.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
110
+ | 107 | bert.encoder.layer.6.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
111
+ | 108 | bert.encoder.layer.6.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
112
+ | 109 | bert.encoder.layer.6.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
113
+ | 110 | bert.encoder.layer.6.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
114
+ | 111 | bert.encoder.layer.6.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
115
+ | 112 | bert.encoder.layer.6.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
116
+ | 113 | bert.encoder.layer.6.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
117
+ | 114 | bert.encoder.layer.6.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
118
+ | 115 | bert.encoder.layer.6.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
119
+ | 116 | bert.encoder.layer.6.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
120
+ | 117 | bert.encoder.layer.7.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
121
+ | 118 | bert.encoder.layer.7.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
122
+ | 119 | bert.encoder.layer.7.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
123
+ | 120 | bert.encoder.layer.7.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
124
+ | 121 | bert.encoder.layer.7.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
125
+ | 122 | bert.encoder.layer.7.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
126
+ | 123 | bert.encoder.layer.7.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
127
+ | 124 | bert.encoder.layer.7.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
128
+ | 125 | bert.encoder.layer.7.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
129
+ | 126 | bert.encoder.layer.7.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
130
+ | 127 | bert.encoder.layer.7.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
131
+ | 128 | bert.encoder.layer.7.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
132
+ | 129 | bert.encoder.layer.7.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
133
+ | 130 | bert.encoder.layer.7.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
134
+ | 131 | bert.encoder.layer.7.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
135
+ | 132 | bert.encoder.layer.7.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
136
+ | 133 | bert.encoder.layer.8.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
137
+ | 134 | bert.encoder.layer.8.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
138
+ | 135 | bert.encoder.layer.8.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
139
+ | 136 | bert.encoder.layer.8.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
140
+ | 137 | bert.encoder.layer.8.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
141
+ | 138 | bert.encoder.layer.8.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
142
+ | 139 | bert.encoder.layer.8.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
143
+ | 140 | bert.encoder.layer.8.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
144
+ | 141 | bert.encoder.layer.8.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
145
+ | 142 | bert.encoder.layer.8.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
146
+ | 143 | bert.encoder.layer.8.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
147
+ | 144 | bert.encoder.layer.8.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
148
+ | 145 | bert.encoder.layer.8.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
149
+ | 146 | bert.encoder.layer.8.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
150
+ | 147 | bert.encoder.layer.8.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
151
+ | 148 | bert.encoder.layer.8.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
152
+ | 149 | bert.encoder.layer.9.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
153
+ | 150 | bert.encoder.layer.9.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
154
+ | 151 | bert.encoder.layer.9.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
155
+ | 152 | bert.encoder.layer.9.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
156
+ | 153 | bert.encoder.layer.9.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
157
+ | 154 | bert.encoder.layer.9.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
158
+ | 155 | bert.encoder.layer.9.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
159
+ | 156 | bert.encoder.layer.9.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
160
+ | 157 | bert.encoder.layer.9.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
161
+ | 158 | bert.encoder.layer.9.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
162
+ | 159 | bert.encoder.layer.9.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
163
+ | 160 | bert.encoder.layer.9.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
164
+ | 161 | bert.encoder.layer.9.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
165
+ | 162 | bert.encoder.layer.9.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
166
+ | 163 | bert.encoder.layer.9.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
167
+ | 164 | bert.encoder.layer.9.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
168
+ | 165 | bert.encoder.layer.10.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
169
+ | 166 | bert.encoder.layer.10.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
170
+ | 167 | bert.encoder.layer.10.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
171
+ | 168 | bert.encoder.layer.10.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
172
+ | 169 | bert.encoder.layer.10.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
173
+ | 170 | bert.encoder.layer.10.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
174
+ | 171 | bert.encoder.layer.10.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
175
+ | 172 | bert.encoder.layer.10.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
176
+ | 173 | bert.encoder.layer.10.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
177
+ | 174 | bert.encoder.layer.10.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
178
+ | 175 | bert.encoder.layer.10.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
179
+ | 176 | bert.encoder.layer.10.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
180
+ | 177 | bert.encoder.layer.10.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
181
+ | 178 | bert.encoder.layer.10.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
182
+ | 179 | bert.encoder.layer.10.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
183
+ | 180 | bert.encoder.layer.10.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
184
+ | 181 | bert.encoder.layer.11.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
185
+ | 182 | bert.encoder.layer.11.attention.self.query | Linear | bias | [768] | 768 | 768 | 0 |
186
+ | 183 | bert.encoder.layer.11.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
187
+ | 184 | bert.encoder.layer.11.attention.self.key | Linear | bias | [768] | 768 | 768 | 0 |
188
+ | 185 | bert.encoder.layer.11.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
189
+ | 186 | bert.encoder.layer.11.attention.self.value | Linear | bias | [768] | 768 | 768 | 0 |
190
+ | 187 | bert.encoder.layer.11.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
191
+ | 188 | bert.encoder.layer.11.attention.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
192
+ | 189 | bert.encoder.layer.11.attention.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
193
+ | 190 | bert.encoder.layer.11.attention.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
194
+ | 191 | bert.encoder.layer.11.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
195
+ | 192 | bert.encoder.layer.11.intermediate.dense | Linear | bias | [3072] | 3072 | 3072 | 0 |
196
+ | 193 | bert.encoder.layer.11.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
197
+ | 194 | bert.encoder.layer.11.output.dense | Linear | bias | [768] | 768 | 768 | 0 |
198
+ | 195 | bert.encoder.layer.11.output.LayerNorm | LayerNorm | weight | [768] | 768 | 768 | 0 |
199
+ | 196 | bert.encoder.layer.11.output.LayerNorm | LayerNorm | bias | [768] | 768 | 768 | 0 |
200
+ | 197 | qa_outputs | Linear | weight | [2, 768] | 1536 | 1536 | 0 |
201
+ | 198 | qa_outputs | Linear | bias | [2] | 2 | 2 | 0 |
linear_layer_sparsity_85M_params_0.00_sparsity.csv ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ,layer_id,layer_type,param_type,shape,nparam,nnz,sparsity
2
+ 5,bert.encoder.layer.0.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
3
+ 7,bert.encoder.layer.0.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
4
+ 9,bert.encoder.layer.0.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
5
+ 11,bert.encoder.layer.0.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
6
+ 15,bert.encoder.layer.0.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
7
+ 17,bert.encoder.layer.0.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
8
+ 21,bert.encoder.layer.1.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
9
+ 23,bert.encoder.layer.1.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
10
+ 25,bert.encoder.layer.1.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
11
+ 27,bert.encoder.layer.1.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
12
+ 31,bert.encoder.layer.1.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
13
+ 33,bert.encoder.layer.1.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
14
+ 37,bert.encoder.layer.2.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
15
+ 39,bert.encoder.layer.2.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
16
+ 41,bert.encoder.layer.2.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
17
+ 43,bert.encoder.layer.2.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
18
+ 47,bert.encoder.layer.2.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
19
+ 49,bert.encoder.layer.2.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
20
+ 53,bert.encoder.layer.3.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
21
+ 55,bert.encoder.layer.3.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
22
+ 57,bert.encoder.layer.3.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
23
+ 59,bert.encoder.layer.3.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
24
+ 63,bert.encoder.layer.3.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
25
+ 65,bert.encoder.layer.3.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
26
+ 69,bert.encoder.layer.4.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
27
+ 71,bert.encoder.layer.4.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
28
+ 73,bert.encoder.layer.4.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
29
+ 75,bert.encoder.layer.4.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
30
+ 79,bert.encoder.layer.4.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
31
+ 81,bert.encoder.layer.4.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
32
+ 85,bert.encoder.layer.5.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
33
+ 87,bert.encoder.layer.5.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
34
+ 89,bert.encoder.layer.5.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
35
+ 91,bert.encoder.layer.5.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
36
+ 95,bert.encoder.layer.5.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
37
+ 97,bert.encoder.layer.5.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
38
+ 101,bert.encoder.layer.6.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
39
+ 103,bert.encoder.layer.6.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
40
+ 105,bert.encoder.layer.6.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
41
+ 107,bert.encoder.layer.6.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
42
+ 111,bert.encoder.layer.6.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
43
+ 113,bert.encoder.layer.6.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
44
+ 117,bert.encoder.layer.7.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
45
+ 119,bert.encoder.layer.7.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
46
+ 121,bert.encoder.layer.7.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
47
+ 123,bert.encoder.layer.7.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
48
+ 127,bert.encoder.layer.7.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
49
+ 129,bert.encoder.layer.7.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
50
+ 133,bert.encoder.layer.8.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
51
+ 135,bert.encoder.layer.8.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
52
+ 137,bert.encoder.layer.8.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
53
+ 139,bert.encoder.layer.8.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
54
+ 143,bert.encoder.layer.8.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
55
+ 145,bert.encoder.layer.8.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
56
+ 149,bert.encoder.layer.9.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
57
+ 151,bert.encoder.layer.9.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
58
+ 153,bert.encoder.layer.9.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
59
+ 155,bert.encoder.layer.9.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
60
+ 159,bert.encoder.layer.9.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
61
+ 161,bert.encoder.layer.9.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
62
+ 165,bert.encoder.layer.10.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
63
+ 167,bert.encoder.layer.10.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
64
+ 169,bert.encoder.layer.10.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
65
+ 171,bert.encoder.layer.10.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
66
+ 175,bert.encoder.layer.10.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
67
+ 177,bert.encoder.layer.10.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
68
+ 181,bert.encoder.layer.11.attention.self.query,Linear,weight,"[768, 768]",589824,589824,0.0
69
+ 183,bert.encoder.layer.11.attention.self.key,Linear,weight,"[768, 768]",589824,589824,0.0
70
+ 185,bert.encoder.layer.11.attention.self.value,Linear,weight,"[768, 768]",589824,589824,0.0
71
+ 187,bert.encoder.layer.11.attention.output.dense,Linear,weight,"[768, 768]",589824,589824,0.0
72
+ 191,bert.encoder.layer.11.intermediate.dense,Linear,weight,"[3072, 768]",2359296,2359296,0.0
73
+ 193,bert.encoder.layer.11.output.dense,Linear,weight,"[768, 3072]",2359296,2359296,0.0
linear_layer_sparsity_85M_params_0.00_sparsity.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | | layer_id | layer_type | param_type | shape | nparam | nnz | sparsity |
2
+ |----:|:---------------------------------------------|:-------------|:-------------|:------------|---------:|--------:|-----------:|
3
+ | 5 | bert.encoder.layer.0.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
4
+ | 7 | bert.encoder.layer.0.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
5
+ | 9 | bert.encoder.layer.0.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
6
+ | 11 | bert.encoder.layer.0.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
7
+ | 15 | bert.encoder.layer.0.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
8
+ | 17 | bert.encoder.layer.0.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
9
+ | 21 | bert.encoder.layer.1.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
10
+ | 23 | bert.encoder.layer.1.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
11
+ | 25 | bert.encoder.layer.1.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
12
+ | 27 | bert.encoder.layer.1.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
13
+ | 31 | bert.encoder.layer.1.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
14
+ | 33 | bert.encoder.layer.1.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
15
+ | 37 | bert.encoder.layer.2.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
16
+ | 39 | bert.encoder.layer.2.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
17
+ | 41 | bert.encoder.layer.2.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
18
+ | 43 | bert.encoder.layer.2.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
19
+ | 47 | bert.encoder.layer.2.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
20
+ | 49 | bert.encoder.layer.2.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
21
+ | 53 | bert.encoder.layer.3.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
22
+ | 55 | bert.encoder.layer.3.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
23
+ | 57 | bert.encoder.layer.3.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
24
+ | 59 | bert.encoder.layer.3.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
25
+ | 63 | bert.encoder.layer.3.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
26
+ | 65 | bert.encoder.layer.3.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
27
+ | 69 | bert.encoder.layer.4.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
28
+ | 71 | bert.encoder.layer.4.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
29
+ | 73 | bert.encoder.layer.4.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
30
+ | 75 | bert.encoder.layer.4.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
31
+ | 79 | bert.encoder.layer.4.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
32
+ | 81 | bert.encoder.layer.4.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
33
+ | 85 | bert.encoder.layer.5.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
34
+ | 87 | bert.encoder.layer.5.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
35
+ | 89 | bert.encoder.layer.5.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
36
+ | 91 | bert.encoder.layer.5.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
37
+ | 95 | bert.encoder.layer.5.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
38
+ | 97 | bert.encoder.layer.5.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
39
+ | 101 | bert.encoder.layer.6.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
40
+ | 103 | bert.encoder.layer.6.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
41
+ | 105 | bert.encoder.layer.6.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
42
+ | 107 | bert.encoder.layer.6.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
43
+ | 111 | bert.encoder.layer.6.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
44
+ | 113 | bert.encoder.layer.6.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
45
+ | 117 | bert.encoder.layer.7.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
46
+ | 119 | bert.encoder.layer.7.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
47
+ | 121 | bert.encoder.layer.7.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
48
+ | 123 | bert.encoder.layer.7.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
49
+ | 127 | bert.encoder.layer.7.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
50
+ | 129 | bert.encoder.layer.7.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
51
+ | 133 | bert.encoder.layer.8.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
52
+ | 135 | bert.encoder.layer.8.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
53
+ | 137 | bert.encoder.layer.8.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
54
+ | 139 | bert.encoder.layer.8.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
55
+ | 143 | bert.encoder.layer.8.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
56
+ | 145 | bert.encoder.layer.8.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
57
+ | 149 | bert.encoder.layer.9.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
58
+ | 151 | bert.encoder.layer.9.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
59
+ | 153 | bert.encoder.layer.9.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
60
+ | 155 | bert.encoder.layer.9.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
61
+ | 159 | bert.encoder.layer.9.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
62
+ | 161 | bert.encoder.layer.9.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
63
+ | 165 | bert.encoder.layer.10.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
64
+ | 167 | bert.encoder.layer.10.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
65
+ | 169 | bert.encoder.layer.10.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
66
+ | 171 | bert.encoder.layer.10.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
67
+ | 175 | bert.encoder.layer.10.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
68
+ | 177 | bert.encoder.layer.10.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |
69
+ | 181 | bert.encoder.layer.11.attention.self.query | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
70
+ | 183 | bert.encoder.layer.11.attention.self.key | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
71
+ | 185 | bert.encoder.layer.11.attention.self.value | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
72
+ | 187 | bert.encoder.layer.11.attention.output.dense | Linear | weight | [768, 768] | 589824 | 589824 | 0 |
73
+ | 191 | bert.encoder.layer.11.intermediate.dense | Linear | weight | [3072, 768] | 2359296 | 2359296 | 0 |
74
+ | 193 | bert.encoder.layer.11.output.dense | Linear | weight | [768, 3072] | 2359296 | 2359296 | 0 |