Hugging Face's logo

neuralmagic
/
oBERT-12-upstream-pruned-unstructured-97

Transformers
PyTorch
English
bert
oBERT
sparsity
pruning
compression
Inference Endpoints
Model card Files Community
ekurtic commited on
Commit
30dfe1f
•
1 Parent(s): 2a18dfa

Add link to code

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -31,9 +31,11 @@ Sparsity: 97%
31
  Number of layers: 12
32
  ```
33
 
34
- Code: _coming soon_
35
 
36
- ## BibTeX entry and citation info
 
 
37
  ```bibtex
38
  @article{kurtic2022optimal,
39
  title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},
 
31
  Number of layers: 12
32
  ```
33
 
34
+ Code: [https://github.com/neuralmagic/sparseml/tree/main/research/optimal_BERT_surgeon_oBERT](https://github.com/neuralmagic/sparseml/tree/main/research/optimal_BERT_surgeon_oBERT)
35
 
36
+ If you find the model useful, please consider citing our work.
37
+
38
+ ## Citation info
39
  ```bibtex
40
  @article{kurtic2022optimal,
41
  title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},