Hugging Face's logo

vuiseng9
/
bert-b-jpqd-r0.0030-9pc-sparse-quantized

Transformers
ONNX
bert
Inference Endpoints
Model card Files Community
Vui Seng Chua commited on
Commit
843224c
•
1 Parent(s): f026bfe

add content

Browse files
Files changed (31) hide show
  1. 8bit_ref_bert_squad_nncf_mvmt.json +67 -0
  2. all_results.json +11 -0
  3. checkpoint-108500/config.json +25 -0
  4. checkpoint-108500/nncf-mvmt-p3.json +1 -0
  5. checkpoint-108500/pytorch_model.bin +3 -0
  6. checkpoint-108500/rng_state.pth +3 -0
  7. checkpoint-108500/scheduler.pt +3 -0
  8. checkpoint-108500/special_tokens_map.json +1 -0
  9. checkpoint-108500/tokenizer.json +0 -0
  10. checkpoint-108500/tokenizer_config.json +1 -0
  11. checkpoint-108500/training_args.bin +3 -0
  12. checkpoint-108500/vocab.txt +0 -0
  13. compressed_graph.dot +0 -0
  14. config.json +25 -0
  15. eval_predictions.json +0 -0
  16. eval_results.json +6 -0
  17. ir/sparsity_structures.csv +73 -0
  18. ir/sparsity_structures.md +74 -0
  19. ir/sparsity_structures.pkl +3 -0
  20. ir/squad-BertForQuestionAnswering.crop_cfg.sd.8bit.pkl +3 -0
  21. ir/squad-BertForQuestionAnswering.cropped.8bit.bin +3 -0
  22. ir/squad-BertForQuestionAnswering.cropped.8bit.mapping +0 -0
  23. ir/squad-BertForQuestionAnswering.cropped.8bit.onnx +3 -0
  24. ir/squad-BertForQuestionAnswering.cropped.8bit.xml +0 -0
  25. original_graph.dot +0 -0
  26. special_tokens_map.json +1 -0
  27. tokenizer.json +0 -0
  28. tokenizer_config.json +1 -0
  29. train_results.json +8 -0
  30. training_args.bin +3 -0
  31. vocab.txt +0 -0
8bit_ref_bert_squad_nncf_mvmt.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "input_info": [
3
+ {
4
+ "sample_size": [1, 384],
5
+ "type": "long"
6
+ },
7
+ {
8
+ "sample_size": [1, 384],
9
+ "type": "long"
10
+ },
11
+ {
12
+ "sample_size": [1, 384],
13
+ "type": "long"
14
+ }
15
+ ],
16
+ "compression":
17
+ [
18
+ {
19
+ "algorithm": "movement_sparsity",
20
+ "params": {
21
+ "schedule": "threshold_polynomial_decay",
22
+ "power": 3,
23
+ "init_importance_threshold": 0.0,
24
+ "final_importance_threshold": 0.1,
25
+ "warmup_start_epoch": 1,
26
+ "warmup_end_epoch": 10,
27
+ "steps_per_epoch": 5533,
28
+ "importance_regularization_factor": 0.0030,
29
+ "update_per_optimizer_step": true,
30
+ },
31
+ "sparse_structure_by_scopes": [
32
+ ["block", [32, 32], "{re}.*BertAttention*"],
33
+ ["per_dim", [0], "{re}.*BertIntermediate*"],
34
+ ["per_dim", [1], "{re}.*BertOutput*"]
35
+ ],
36
+ "ignored_scopes": ["{re}.*NNCFEmbedding", "{re}.*qa_outputs*"]
37
+ },
38
+ {
39
+ "algorithm": "quantization",
40
+ "initializer": {
41
+ "range": {
42
+ "num_init_samples": 32,
43
+ "type": "percentile",
44
+ "params":
45
+ {
46
+ "min_percentile": 0.01,
47
+ "max_percentile": 99.99
48
+ }
49
+ },
50
+
51
+ "batchnorm_adaptation": {
52
+ "num_bn_adaptation_samples": 200
53
+ }
54
+ },
55
+ "activations":
56
+ {
57
+ "mode": "symmetric"
58
+ },
59
+ "weights":
60
+ {
61
+ "mode": "symmetric",
62
+ "signed": true,
63
+ "per_channel": false
64
+ }
65
+ }
66
+ ]
67
+ }
all_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "eval_exact_match": 84.41816461684012,
4
+ "eval_f1": 90.81487117813558,
5
+ "eval_samples": 10784,
6
+ "train_loss": 0.664879799468186,
7
+ "train_runtime": 241846.7637,
8
+ "train_samples": 88524,
9
+ "train_samples_per_second": 7.321,
10
+ "train_steps_per_second": 0.458
11
+ }
checkpoint-108500/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "NNCFNetwork"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
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
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.9.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
checkpoint-108500/nncf-mvmt-p3.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ../8bit_ref_bert_squad_nncf_mvmt.json
checkpoint-108500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9995c667c4febcd342138aedb109ce54ec5545c820c3880507556a6d3f62e37
3
+ size 776898425
checkpoint-108500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98deea5d84df8bc857dd36b735f209af7a30da6b0257d7febb3bdd4024822c0e
3
+ size 14503
checkpoint-108500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3755b619c2b849d49510fd66e67a4331875f90b17fc96d8f3ecfacd98aa0cf67
3
+ size 623
checkpoint-108500/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
checkpoint-108500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-108500/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
checkpoint-108500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b58f0f9c6195a9e08d4aaa144910c6c2ea7a390458d56167e4292dd7fcc937
3
+ size 3055
checkpoint-108500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
compressed_graph.dot ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "bert-base-uncased",
3
+ "architectures": [
4
+ "NNCFNetwork"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "gradient_checkpointing": false,
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
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.9.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 30522
25
+ }
eval_predictions.json ADDED
The diff for this file is too large to render. See raw diff
 
eval_results.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "eval_exact_match": 84.41816461684012,
4
+ "eval_f1": 90.81487117813558,
5
+ "eval_samples": 10784
6
+ }
ir/sparsity_structures.csv ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ pt_module_name,block_id,orig_w_shape,final_w_shape,orig_b_shape,final_b_shape,prune_by,id_to_keep,head_id_to_keep,nncf_graph_node
2
+ nncf_module.bert.encoder.layer.0.attention.self.key,0,"(768, 768)","(384, 768)","(768,)","(384,)",group of 64 rows,See pkl,"[0, 1, 3, 8, 9, 10]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
3
+ nncf_module.bert.encoder.layer.0.attention.self.value,0,"(768, 768)","(384, 768)","(768,)","(384,)",group of 64 rows,See pkl,"[0, 1, 3, 8, 9, 10]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
4
+ nncf_module.bert.encoder.layer.0.attention.self.query,0,"(768, 768)","(384, 768)","(768,)","(384,)",group of 64 rows,See pkl,"[0, 1, 3, 8, 9, 10]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
5
+ nncf_module.bert.encoder.layer.0.attention.output.dense,0,"(768, 768)","(768, 384)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 3, 8, 9, 10]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
6
+ nncf_module.bert.encoder.layer.0.intermediate.dense,1,"(3072, 768)","(3048, 768)","(3072,)","(3048,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
7
+ nncf_module.bert.encoder.layer.0.output.dense,1,"(768, 3072)","(768, 3048)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/linear_0
8
+ nncf_module.bert.encoder.layer.1.attention.self.query,2,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
9
+ nncf_module.bert.encoder.layer.1.attention.self.value,2,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
10
+ nncf_module.bert.encoder.layer.1.attention.self.key,2,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
11
+ nncf_module.bert.encoder.layer.1.attention.output.dense,2,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
12
+ nncf_module.bert.encoder.layer.1.intermediate.dense,3,"(3072, 768)","(3033, 768)","(3072,)","(3033,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
13
+ nncf_module.bert.encoder.layer.1.output.dense,3,"(768, 3072)","(768, 3033)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/linear_0
14
+ nncf_module.bert.encoder.layer.2.attention.self.value,4,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
15
+ nncf_module.bert.encoder.layer.2.attention.output.dense,4,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
16
+ nncf_module.bert.encoder.layer.2.attention.self.key,4,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
17
+ nncf_module.bert.encoder.layer.2.attention.self.query,4,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
18
+ nncf_module.bert.encoder.layer.2.output.dense,5,"(768, 3072)","(768, 3040)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/linear_0
19
+ nncf_module.bert.encoder.layer.2.intermediate.dense,5,"(3072, 768)","(3040, 768)","(3072,)","(3040,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
20
+ nncf_module.bert.encoder.layer.3.attention.output.dense,6,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
21
+ nncf_module.bert.encoder.layer.3.attention.self.query,6,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
22
+ nncf_module.bert.encoder.layer.3.attention.self.value,6,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
23
+ nncf_module.bert.encoder.layer.3.attention.self.key,6,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
24
+ nncf_module.bert.encoder.layer.3.intermediate.dense,7,"(3072, 768)","(3048, 768)","(3072,)","(3048,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
25
+ nncf_module.bert.encoder.layer.3.output.dense,7,"(768, 3072)","(768, 3048)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/linear_0
26
+ nncf_module.bert.encoder.layer.4.attention.self.value,8,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
27
+ nncf_module.bert.encoder.layer.4.attention.output.dense,8,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
28
+ nncf_module.bert.encoder.layer.4.attention.self.key,8,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
29
+ nncf_module.bert.encoder.layer.4.attention.self.query,8,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
30
+ nncf_module.bert.encoder.layer.4.intermediate.dense,9,"(3072, 768)","(3023, 768)","(3072,)","(3023,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
31
+ nncf_module.bert.encoder.layer.4.output.dense,9,"(768, 3072)","(768, 3023)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/linear_0
32
+ nncf_module.bert.encoder.layer.5.attention.self.key,10,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
33
+ nncf_module.bert.encoder.layer.5.attention.self.value,10,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
34
+ nncf_module.bert.encoder.layer.5.attention.output.dense,10,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
35
+ nncf_module.bert.encoder.layer.5.attention.self.query,10,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
36
+ nncf_module.bert.encoder.layer.5.output.dense,11,"(768, 3072)","(768, 2999)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/linear_0
37
+ nncf_module.bert.encoder.layer.5.intermediate.dense,11,"(3072, 768)","(2999, 768)","(3072,)","(2999,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
38
+ nncf_module.bert.encoder.layer.6.attention.self.query,12,"(768, 768)","(640, 768)","(768,)","(640,)",group of 64 rows,See pkl,"[0, 1, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
39
+ nncf_module.bert.encoder.layer.6.attention.self.value,12,"(768, 768)","(640, 768)","(768,)","(640,)",group of 64 rows,See pkl,"[0, 1, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
40
+ nncf_module.bert.encoder.layer.6.attention.output.dense,12,"(768, 768)","(768, 640)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
41
+ nncf_module.bert.encoder.layer.6.attention.self.key,12,"(768, 768)","(640, 768)","(768,)","(640,)",group of 64 rows,See pkl,"[0, 1, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
42
+ nncf_module.bert.encoder.layer.6.output.dense,13,"(768, 3072)","(768, 2960)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/linear_0
43
+ nncf_module.bert.encoder.layer.6.intermediate.dense,13,"(3072, 768)","(2960, 768)","(3072,)","(2960,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
44
+ nncf_module.bert.encoder.layer.7.attention.self.query,14,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
45
+ nncf_module.bert.encoder.layer.7.attention.output.dense,14,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
46
+ nncf_module.bert.encoder.layer.7.attention.self.key,14,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
47
+ nncf_module.bert.encoder.layer.7.attention.self.value,14,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
48
+ nncf_module.bert.encoder.layer.7.output.dense,15,"(768, 3072)","(768, 2946)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/linear_0
49
+ nncf_module.bert.encoder.layer.7.intermediate.dense,15,"(3072, 768)","(2946, 768)","(3072,)","(2946,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
50
+ nncf_module.bert.encoder.layer.8.attention.self.value,16,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
51
+ nncf_module.bert.encoder.layer.8.attention.self.key,16,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
52
+ nncf_module.bert.encoder.layer.8.attention.self.query,16,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
53
+ nncf_module.bert.encoder.layer.8.attention.output.dense,16,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
54
+ nncf_module.bert.encoder.layer.8.output.dense,17,"(768, 3072)","(768, 2857)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/linear_0
55
+ nncf_module.bert.encoder.layer.8.intermediate.dense,17,"(3072, 768)","(2857, 768)","(3072,)","(2857,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
56
+ nncf_module.bert.encoder.layer.9.attention.self.query,18,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
57
+ nncf_module.bert.encoder.layer.9.attention.self.key,18,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
58
+ nncf_module.bert.encoder.layer.9.attention.self.value,18,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
59
+ nncf_module.bert.encoder.layer.9.attention.output.dense,18,"(768, 768)","(768, 768)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
60
+ nncf_module.bert.encoder.layer.9.intermediate.dense,19,"(3072, 768)","(2688, 768)","(3072,)","(2688,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
61
+ nncf_module.bert.encoder.layer.9.output.dense,19,"(768, 3072)","(768, 2688)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/linear_0
62
+ nncf_module.bert.encoder.layer.10.attention.output.dense,20,"(768, 768)","(768, 320)","(768,)","(768,)",group of 64 cols,See pkl,"[3, 7, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
63
+ nncf_module.bert.encoder.layer.10.attention.self.key,20,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[3, 7, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
64
+ nncf_module.bert.encoder.layer.10.attention.self.value,20,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[3, 7, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
65
+ nncf_module.bert.encoder.layer.10.attention.self.query,20,"(768, 768)","(320, 768)","(768,)","(320,)",group of 64 rows,See pkl,"[3, 7, 9, 10, 11]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
66
+ nncf_module.bert.encoder.layer.10.intermediate.dense,21,"(3072, 768)","(2579, 768)","(3072,)","(2579,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
67
+ nncf_module.bert.encoder.layer.10.output.dense,21,"(768, 3072)","(768, 2579)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/linear_0
68
+ nncf_module.bert.encoder.layer.11.attention.output.dense,22,"(768, 768)","(768, 384)","(768,)","(768,)",group of 64 cols,See pkl,"[0, 1, 2, 3, 4, 8]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0
69
+ nncf_module.bert.encoder.layer.11.attention.self.value,22,"(768, 768)","(384, 768)","(768,)","(384,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 8]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0
70
+ nncf_module.bert.encoder.layer.11.attention.self.key,22,"(768, 768)","(384, 768)","(768,)","(384,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 8]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0
71
+ nncf_module.bert.encoder.layer.11.attention.self.query,22,"(768, 768)","(384, 768)","(768,)","(384,)",group of 64 rows,See pkl,"[0, 1, 2, 3, 4, 8]",BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0
72
+ nncf_module.bert.encoder.layer.11.output.dense,23,"(768, 3072)","(768, 2465)","(768,)","(768,)",col,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/linear_0
73
+ nncf_module.bert.encoder.layer.11.intermediate.dense,23,"(3072, 768)","(2465, 768)","(3072,)","(2465,)",row,See pkl,,BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0
ir/sparsity_structures.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ | | pt_module_name | block_id | orig_w_shape | final_w_shape | orig_b_shape | final_b_shape | prune_by | id_to_keep | head_id_to_keep | nncf_graph_node |
2
+ |---:|:---------------------------------------------------------|-----------:|:---------------|:----------------|:---------------|:----------------|:-----------------|:-------------|:---------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
3
+ | 0 | nncf_module.bert.encoder.layer.0.attention.self.key | 0 | (768, 768) | (384, 768) | (768,) | (384,) | group of 64 rows | See pkl | [0, 1, 3, 8, 9, 10] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
4
+ | 1 | nncf_module.bert.encoder.layer.0.attention.self.value | 0 | (768, 768) | (384, 768) | (768,) | (384,) | group of 64 rows | See pkl | [0, 1, 3, 8, 9, 10] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
5
+ | 2 | nncf_module.bert.encoder.layer.0.attention.self.query | 0 | (768, 768) | (384, 768) | (768,) | (384,) | group of 64 rows | See pkl | [0, 1, 3, 8, 9, 10] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
6
+ | 3 | nncf_module.bert.encoder.layer.0.attention.output.dense | 0 | (768, 768) | (768, 384) | (768,) | (768,) | group of 64 cols | See pkl | [0, 1, 3, 8, 9, 10] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
7
+ | 4 | nncf_module.bert.encoder.layer.0.intermediate.dense | 1 | (3072, 768) | (3048, 768) | (3072,) | (3048,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
8
+ | 5 | nncf_module.bert.encoder.layer.0.output.dense | 1 | (768, 3072) | (768, 3048) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[0]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
9
+ | 6 | nncf_module.bert.encoder.layer.1.attention.self.query | 2 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
10
+ | 7 | nncf_module.bert.encoder.layer.1.attention.self.value | 2 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
11
+ | 8 | nncf_module.bert.encoder.layer.1.attention.self.key | 2 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
12
+ | 9 | nncf_module.bert.encoder.layer.1.attention.output.dense | 2 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 cols | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
13
+ | 10 | nncf_module.bert.encoder.layer.1.intermediate.dense | 3 | (3072, 768) | (3033, 768) | (3072,) | (3033,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
14
+ | 11 | nncf_module.bert.encoder.layer.1.output.dense | 3 | (768, 3072) | (768, 3033) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[1]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
15
+ | 12 | nncf_module.bert.encoder.layer.2.attention.self.value | 4 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
16
+ | 13 | nncf_module.bert.encoder.layer.2.attention.output.dense | 4 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 cols | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
17
+ | 14 | nncf_module.bert.encoder.layer.2.attention.self.key | 4 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
18
+ | 15 | nncf_module.bert.encoder.layer.2.attention.self.query | 4 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
19
+ | 16 | nncf_module.bert.encoder.layer.2.output.dense | 5 | (768, 3072) | (768, 3040) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
20
+ | 17 | nncf_module.bert.encoder.layer.2.intermediate.dense | 5 | (3072, 768) | (3040, 768) | (3072,) | (3040,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[2]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
21
+ | 18 | nncf_module.bert.encoder.layer.3.attention.output.dense | 6 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 cols | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
22
+ | 19 | nncf_module.bert.encoder.layer.3.attention.self.query | 6 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
23
+ | 20 | nncf_module.bert.encoder.layer.3.attention.self.value | 6 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
24
+ | 21 | nncf_module.bert.encoder.layer.3.attention.self.key | 6 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
25
+ | 22 | nncf_module.bert.encoder.layer.3.intermediate.dense | 7 | (3072, 768) | (3048, 768) | (3072,) | (3048,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
26
+ | 23 | nncf_module.bert.encoder.layer.3.output.dense | 7 | (768, 3072) | (768, 3048) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[3]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
27
+ | 24 | nncf_module.bert.encoder.layer.4.attention.self.value | 8 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
28
+ | 25 | nncf_module.bert.encoder.layer.4.attention.output.dense | 8 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 cols | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
29
+ | 26 | nncf_module.bert.encoder.layer.4.attention.self.key | 8 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
30
+ | 27 | nncf_module.bert.encoder.layer.4.attention.self.query | 8 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
31
+ | 28 | nncf_module.bert.encoder.layer.4.intermediate.dense | 9 | (3072, 768) | (3023, 768) | (3072,) | (3023,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
32
+ | 29 | nncf_module.bert.encoder.layer.4.output.dense | 9 | (768, 3072) | (768, 3023) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[4]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
33
+ | 30 | nncf_module.bert.encoder.layer.5.attention.self.key | 10 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
34
+ | 31 | nncf_module.bert.encoder.layer.5.attention.self.value | 10 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
35
+ | 32 | nncf_module.bert.encoder.layer.5.attention.output.dense | 10 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 cols | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
36
+ | 33 | nncf_module.bert.encoder.layer.5.attention.self.query | 10 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
37
+ | 34 | nncf_module.bert.encoder.layer.5.output.dense | 11 | (768, 3072) | (768, 2999) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
38
+ | 35 | nncf_module.bert.encoder.layer.5.intermediate.dense | 11 | (3072, 768) | (2999, 768) | (3072,) | (2999,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[5]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
39
+ | 36 | nncf_module.bert.encoder.layer.6.attention.self.query | 12 | (768, 768) | (640, 768) | (768,) | (640,) | group of 64 rows | See pkl | [0, 1, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
40
+ | 37 | nncf_module.bert.encoder.layer.6.attention.self.value | 12 | (768, 768) | (640, 768) | (768,) | (640,) | group of 64 rows | See pkl | [0, 1, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
41
+ | 38 | nncf_module.bert.encoder.layer.6.attention.output.dense | 12 | (768, 768) | (768, 640) | (768,) | (768,) | group of 64 cols | See pkl | [0, 1, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
42
+ | 39 | nncf_module.bert.encoder.layer.6.attention.self.key | 12 | (768, 768) | (640, 768) | (768,) | (640,) | group of 64 rows | See pkl | [0, 1, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
43
+ | 40 | nncf_module.bert.encoder.layer.6.output.dense | 13 | (768, 3072) | (768, 2960) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
44
+ | 41 | nncf_module.bert.encoder.layer.6.intermediate.dense | 13 | (3072, 768) | (2960, 768) | (3072,) | (2960,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[6]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
45
+ | 42 | nncf_module.bert.encoder.layer.7.attention.self.query | 14 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
46
+ | 43 | nncf_module.bert.encoder.layer.7.attention.output.dense | 14 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 cols | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
47
+ | 44 | nncf_module.bert.encoder.layer.7.attention.self.key | 14 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
48
+ | 45 | nncf_module.bert.encoder.layer.7.attention.self.value | 14 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
49
+ | 46 | nncf_module.bert.encoder.layer.7.output.dense | 15 | (768, 3072) | (768, 2946) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
50
+ | 47 | nncf_module.bert.encoder.layer.7.intermediate.dense | 15 | (3072, 768) | (2946, 768) | (3072,) | (2946,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[7]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
51
+ | 48 | nncf_module.bert.encoder.layer.8.attention.self.value | 16 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
52
+ | 49 | nncf_module.bert.encoder.layer.8.attention.self.key | 16 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
53
+ | 50 | nncf_module.bert.encoder.layer.8.attention.self.query | 16 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
54
+ | 51 | nncf_module.bert.encoder.layer.8.attention.output.dense | 16 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 cols | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
55
+ | 52 | nncf_module.bert.encoder.layer.8.output.dense | 17 | (768, 3072) | (768, 2857) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
56
+ | 53 | nncf_module.bert.encoder.layer.8.intermediate.dense | 17 | (3072, 768) | (2857, 768) | (3072,) | (2857,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[8]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
57
+ | 54 | nncf_module.bert.encoder.layer.9.attention.self.query | 18 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
58
+ | 55 | nncf_module.bert.encoder.layer.9.attention.self.key | 18 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
59
+ | 56 | nncf_module.bert.encoder.layer.9.attention.self.value | 18 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
60
+ | 57 | nncf_module.bert.encoder.layer.9.attention.output.dense | 18 | (768, 768) | (768, 768) | (768,) | (768,) | group of 64 cols | See pkl | [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
61
+ | 58 | nncf_module.bert.encoder.layer.9.intermediate.dense | 19 | (3072, 768) | (2688, 768) | (3072,) | (2688,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
62
+ | 59 | nncf_module.bert.encoder.layer.9.output.dense | 19 | (768, 3072) | (768, 2688) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[9]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
63
+ | 60 | nncf_module.bert.encoder.layer.10.attention.output.dense | 20 | (768, 768) | (768, 320) | (768,) | (768,) | group of 64 cols | See pkl | [3, 7, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
64
+ | 61 | nncf_module.bert.encoder.layer.10.attention.self.key | 20 | (768, 768) | (320, 768) | (768,) | (320,) | group of 64 rows | See pkl | [3, 7, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
65
+ | 62 | nncf_module.bert.encoder.layer.10.attention.self.value | 20 | (768, 768) | (320, 768) | (768,) | (320,) | group of 64 rows | See pkl | [3, 7, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
66
+ | 63 | nncf_module.bert.encoder.layer.10.attention.self.query | 20 | (768, 768) | (320, 768) | (768,) | (320,) | group of 64 rows | See pkl | [3, 7, 9, 10, 11] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
67
+ | 64 | nncf_module.bert.encoder.layer.10.intermediate.dense | 21 | (3072, 768) | (2579, 768) | (3072,) | (2579,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
68
+ | 65 | nncf_module.bert.encoder.layer.10.output.dense | 21 | (768, 3072) | (768, 2579) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[10]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
69
+ | 66 | nncf_module.bert.encoder.layer.11.attention.output.dense | 22 | (768, 768) | (768, 384) | (768,) | (768,) | group of 64 cols | See pkl | [0, 1, 2, 3, 4, 8] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfOutput[output]/NNCFLinear[dense]/linear_0 |
70
+ | 67 | nncf_module.bert.encoder.layer.11.attention.self.value | 22 | (768, 768) | (384, 768) | (768,) | (384,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 8] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[value]/linear_0 |
71
+ | 68 | nncf_module.bert.encoder.layer.11.attention.self.key | 22 | (768, 768) | (384, 768) | (768,) | (384,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 8] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[key]/linear_0 |
72
+ | 69 | nncf_module.bert.encoder.layer.11.attention.self.query | 22 | (768, 768) | (384, 768) | (768,) | (384,) | group of 64 rows | See pkl | [0, 1, 2, 3, 4, 8] | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertAttention[attention]/BertSelfAttention[self]/NNCFLinear[query]/linear_0 |
73
+ | 70 | nncf_module.bert.encoder.layer.11.output.dense | 23 | (768, 3072) | (768, 2465) | (768,) | (768,) | col | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertOutput[output]/NNCFLinear[dense]/linear_0 |
74
+ | 71 | nncf_module.bert.encoder.layer.11.intermediate.dense | 23 | (3072, 768) | (2465, 768) | (3072,) | (2465,) | row | See pkl | | BertForQuestionAnswering/BertModel[bert]/BertEncoder[encoder]/ModuleList[layer]/BertLayer[11]/BertIntermediate[intermediate]/NNCFLinear[dense]/linear_0 |
ir/sparsity_structures.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2227976475539441e6174c035c8de0fb1fe549afe0de03290d3ae793e1d33886
3
+ size 309999
ir/squad-BertForQuestionAnswering.crop_cfg.sd.8bit.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6e95b468e67f5046fc2ddac876019bb569312aaea46dd0a885b8f5fc202eb2
3
+ size 406204953
ir/squad-BertForQuestionAnswering.cropped.8bit.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0c94e21faff2b94443d42309724ee28f9172b3277b6aca25a1259602a502bf9
3
+ size 101764176
ir/squad-BertForQuestionAnswering.cropped.8bit.mapping ADDED
The diff for this file is too large to render. See raw diff
 
ir/squad-BertForQuestionAnswering.cropped.8bit.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:243deb9b299cb1ad5c35e3c46c6310c0d7c47139693cd5625f631d28903851bf
3
+ size 405795408
ir/squad-BertForQuestionAnswering.cropped.8bit.xml ADDED
The diff for this file is too large to render. See raw diff
 
original_graph.dot ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "BertTokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 20.0,
3
+ "train_loss": 0.664879799468186,
4
+ "train_runtime": 241846.7637,
5
+ "train_samples": 88524,
6
+ "train_samples_per_second": 7.321,
7
+ "train_steps_per_second": 0.458
8
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02b58f0f9c6195a9e08d4aaa144910c6c2ea7a390458d56167e4292dd7fcc937
3
+ size 3055
vocab.txt ADDED
The diff for this file is too large to render. See raw diff