Model release

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,32 @@
+# oBERT-12-downstream-pruned-block4-90-QAT-squadv1
+
+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).
+
+
+It corresponds to the model presented in the `Table 3 - 12 Layers - Sparsity 90% - 4-block + QAT`.
+
+```
+Pruning method: oBERT downstream block-4 + QAT
+Paper: https://arxiv.org/abs/2203.07259
+Dataset: SQuADv1
+Sparsity: 90%
+Number of layers: 12
+```
+
+The dev-set performance of this model:
+```
+EM = 78.84
+F1 = 86.68
+```
+
+Code: _coming soon_
+
+## BibTeX entry and citation info
+```bibtex
+@article{kurtic2022optimal,
+  title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},
+  author={Kurtic, Eldar and Campos, Daniel and Nguyen, Tuan and Frantar, Elias and Kurtz, Mark and Fineran, Benjamin and Goin, Michael and Alistarh, Dan},
+  journal={arXiv preprint arXiv:2203.07259},
+  year={2022}
+}
+```

all_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40d6856bcf734ec4e873ee2d5ebd1f12c4ec3ea4a21420b0650ee9654061a90
+size 253

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba40a8b7c1cc13bc857bf31b02116d27d84738807807ff2d5a55c3ddf03b18c2
+size 738

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de32876da4d81a85309fe7f92de3ba19e7fe00ca66ae3af79397cdbd7b8259bf
+size 49361811

eval_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a083bf3082b0ed9b1df6b71610550608b857a6d588481de5ad48d6c2a2c54685
+size 589386

eval_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66c85719f05c8793eac31d2968b97e5ed2a15cd6791fac28126c3e1d791787c
+size 115

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb299f5c1d2bc10b5c53458a7ba3e3a44516d0cc5c146cdf3e1a3e10bee27481
+size 436619715

recipe.yaml

@@ -0,0 +1,8 @@
+!QuantizationModifier
+    disable_quantization_observer_epoch: 5
+    end_epoch: -1.0
+    freeze_bn_stats_epoch: 5
+    quantize_embeddings: 1
+    start_epoch: 0.0
+    submodules: ['qa_outputs', 'bert.embeddings', 'bert.encoder']
+

special_tokens_map.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303df45a03609e4ead04bc3dc1536d0ab19b5358db685b6f3da123d05ec200e3
+size 112

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd1c882abbd30517dced455a2c9768945ec726b96727927e4959348d9de550b
+size 466081

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d3d4d2ced002f90895b722862032bf28a2b259a1d23151238381eecad83bb89
+size 452

train_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9dc4f811bae9bae240cc6b6dc6f2d79aebe9521790222af6dce013923e98d0f
+size 159

trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a403352f671c1b4c676bb1b158090779ffd4ca545f1781f7c3145f76d523f9d4
+size 7230

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b318a85149e8f7a13a73b432b0ced47ea94cad20e278c502ef89b0d80cab5e
+size 2607