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 +1,25 @@
+# oBERT-3-downstream-dense-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 - 3 Layers - 0% Sparsity`, and it represents an upper bound for performance of the corresponding pruned models:
+- 80% unstructured: `neuralmagic/oBERT-3-downstream-pruned-unstructured-80-squadv1`
+- 80% block-4: `neuralmagic/oBERT-3-downstream-pruned-block4-80-squadv1`
+- 90% unstructured: `neuralmagic/oBERT-3-downstream-pruned-unstructured-90-squadv1`
+- 90% block-4: `neuralmagic/oBERT-3-downstream-pruned-block4-90-squadv1`
+
+SQuADv1 dev-set:
+```
+EM = 76.62
+F1 = 84.65
+```
+
+## 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 = 76.62251655629139
+f1 = 84.6456696034392
+epoch = 30.0

nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f459900ce90a6c1cacd5079b18cee301ecb8c88aa24803b1094ebc34d1976832
+size 45899659

predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1198acb35fbeae2ecd66f7d590c5983552986d1ce69eb7476b23980391919c5
+size 599672

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24a95ffb11ef70c4ac27d125c8f6a3526c98297404a0d253e2ab024a39f4c683
+size 180436839

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:d0fc8a65ffe6d0ffb2b7970694243c792efd39178c04079608ade29d79c816a3
+size 362

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df1c1f6330eb2ff14bbbc4696c32641aaad3b287bd008b308e301c864786d60b
+size 2415