ekurtic commited on
Commit
cb28127
1 Parent(s): f00f411

Model release

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ 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
+ *.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # oBERT-6-downstream-pruned-block4-90-QAT-squadv1
2
+
3
+ This model is obtained with [The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models](https://arxiv.org/abs/2203.07259).
4
+
5
+
6
+ It corresponds to the model presented in the `Table 3 - 6 Layers - Sparsity 90% - 4-block + QAT`.
7
+
8
+ ```
9
+ Pruning method: oBERT downstream block-4 + QAT
10
+ Paper: https://arxiv.org/abs/2203.07259
11
+ Dataset: SQuADv1
12
+ Sparsity: 90%
13
+ Number of layers: 6
14
+ ```
15
+
16
+ The dev-set performance of this model:
17
+ ```
18
+ EM = 76.56
19
+ F1 = 84.59
20
+ ```
21
+
22
+ Code: _coming soon_
23
+
24
+ ## BibTeX entry and citation info
25
+ ```bibtex
26
+ @article{kurtic2022optimal,
27
+ title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},
28
+ author={Kurtic, Eldar and Campos, Daniel and Nguyen, Tuan and Frantar, Elias and Kurtz, Mark and Fineran, Benjamin and Goin, Michael and Alistarh, Dan},
29
+ journal={arXiv preprint arXiv:2203.07259},
30
+ year={2022}
31
+ }
32
+ ```
all_results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09295d37eea2b22d8944ad21b29d2bd220d39020baa8344251bcf479561437fd
3
+ size 253
config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0d0eaa3cec650ac4f018fb2a0e2f7fd4fa63b0d1d03b952c6204a58a6eb832a
3
+ size 678
eval_nbest_predictions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:001d65e9ee00893089ad353fb8c79d554027510e0c9c42ee8060e0e8ce295687
3
+ size 49244854
eval_predictions.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:207b10b7ac05bee370ec17f5c78bffb682952b16c5be43bbf3b5747365111c0d
3
+ size 589315
eval_results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e0c736973b296c5a0ebca241f65e6489ecf8828ee41e0afab191a21dce49afc
3
+ size 115
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f631f36b0609d20dcc0cdbbca1d171d417656e0726664e2ca0992c3ae9e93e5
3
+ size 266036691
recipe.yaml ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !LayerPruningModifier
2
+ end_epoch: -1.0
3
+ layers: ['bert.encoder.layer.6', 'bert.encoder.layer.7', 'bert.encoder.layer.8', 'bert.encoder.layer.9', 'bert.encoder.layer.10', 'bert.encoder.layer.11']
4
+ start_epoch: -1.0
5
+ update_frequency: -1.0
6
+
7
+ !QuantizationModifier
8
+ disable_quantization_observer_epoch: 5.0
9
+ end_epoch: -1.0
10
+ freeze_bn_stats_epoch: 5.0
11
+ quantize_embeddings: 1
12
+ start_epoch: 0.0
13
+ submodules: ['qa_outputs', 'bert.embeddings', 'bert.encoder']
14
+
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303df45a03609e4ead04bc3dc1536d0ab19b5358db685b6f3da123d05ec200e3
3
+ size 112
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd1c882abbd30517dced455a2c9768945ec726b96727927e4959348d9de550b
3
+ size 466081
tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f79b87350a5d32b0d9462fefcc3bdb4114609aef042160d086942590af7a0b7e
3
+ size 392
train_results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d39e3752046c424bf937a5712952fbbf8af311108bcb654e2a4f7c041a7148e6
3
+ size 159
trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:687b5a6c0bdfb1871bc7f64050bf86b98169290e5f2a5abeb1ccaab1756d876e
3
+ size 7336
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa3639c583303fd80d77a65b3baf26494af7825c6d7a10087fde1706aee67d0c
3
+ size 2607
vocab.txt ADDED
The diff for this file is too large to render. See raw diff