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 +1,39 @@
+# oBERT-12-downstream-pruned-unstructured-97-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 1 - 30 Epochs - oBERT - SQuADv1 97%`.
+
+```
+Pruning method: oBERT downstream unstructured
+Paper: https://arxiv.org/abs/2203.07259
+Dataset: SQuADv1
+Sparsity: 97%
+Number of layers: 12
+```
+
+The dev-set performance reported in the paper is averaged over three seeds, and we release the best model (marked with `(*)`):
+
+```
+| oBERT 97%    | F1    | EM    |
+| ------------ | ----- | ----- |
+| seed=42   (*)| 86.06 | 78.28 |
+| seed=3407    | 86.04 | 78.12 |
+| seed=54321   | 85.85 | 77.93 |
+| ------------ | ----- | ----- |
+| mean         | 85.98 | 78.11 |
+| stdev        | 0.115 | 0.175 |
+```
+
+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}
+}
+```

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8486603b13aa568cb30a3f12f76029a3365344a234ace7353010ea02ea15338
+size 659

eval_results.txt

@@ -0,0 +1,3 @@
+exact_match = 78.27814569536424
+f1 = 86.06284342742502
+epoch = 30.0

nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ca9c31f21d35ebdee8ad15dbb90036b5dfa3f1bea09977dbc92f1ccd7e3e99
+size 45808357

predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fa81b3a3a46d065d0fda693124bf21e6e12eca003bd7331969a0d3cd6ccb694
+size 588547

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41219939126ae2417f3eabc2bbcbb10187cd250e263f90c83ffb075b17bb963
+size 435661303

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a863c20bb9664ba983f10e20d34c790e0eea92f165fc4716c4bad62f6bdc70b4
+size 285

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8ad900c72c6d0018dcbaa58356e0781eca1f5beacec423911aac6dca126833
+size 2415