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-80-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 80%`.
+
+```
+Pruning method: oBERT downstream unstructured
+Paper: https://arxiv.org/abs/2203.07259
+Dataset: QQP
+Sparsity: 80%
+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 80%    | acc   | F1    |
+| ------------ | ----- | ----- |
+| seed=42   (*)| 91.66 | 88.72 |
+| seed=3407    | 91.51 | 88.56 |
+| seed=54321   | 91.54 | 88.60 |
+| ------------ | ----- | ----- |
+| mean         | 91.57 | 88.63 |
+| stdev        | 0.079 | 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 sha256:1ad535d6bbb3db215d328fb419aacc63367e76d2fca0aad1e5fd06f978ce1e84
+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 sha256:87fefd345b07c8e058b85ddd81ec851f6d7986daf1afb2881d593febc6bfccf8
+size 438

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c5637dc6a6e5c2e08b0fbc51de459775362f0de6e564f26676c48aeb0dc7f4
+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 sha256:48cf64484a52bab200a703254a9d1736edb350166f7f10a80f85c1c66c6afc6d
+size 473

trainer_state.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aed676a5da414ef0f06e69da4c0e28ba0cde2e6b44723dcef6afdf2270c779a
+size 93685

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:814362915fc1843e5eb3c173600c783de6288f549fa0b2bf2c0792937214242c
+size 2415