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-qqp
+
+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 - QQP 97%`.
+
+```
+Pruning method: oBERT downstream unstructured
+Paper: https://arxiv.org/abs/2203.07259
+Dataset: QQP
+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%    | acc   | F1    |
+| ------------ | ----- | ----- |
+| seed=42   (*)| 90.90 | 87.73 |
+| seed=3407    | 90.80 | 87.57 |
+| seed=54321   | 90.90 | 87.69 |
+| ------------ | ----- | ----- |
+| mean         | 90.87 | 87.66 |
+| stdev        | 0.057 | 0.083 |
+```
+
+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 sha256:0a6108b10f3a84f7b8b1cf29642feecab24da2446031b1a775f1f9b055c35067
+size 890

config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17f4bc8a78be847cb5ed1d04ca2c60ba026c4f7145f32c150091612d321d6a29
+size 669

eval_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de146a60327af0d35be25b2ca7daef382e6ed4f0d3d9b538f89de710b66ca2b
+size 438

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:255e1e47e6c4a47c85c9a5b3a3448da69dadfb1b69fe3f3b2c078f46be34ba92
+size 438024457

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

train_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f57155dd2e1a4074a2bef347deefb9d6770e0504f84d13cff70e425910c395
+size 473

trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28844365d5fe06f26f56cd19abe48b22c838cd09365e202dff1b3461f5c6d9d1
+size 93702

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5a8e033b5a3536466373bebe4aac9144e77ce4bb8d823d2e8d00b72ba93093a
+size 2415