Hugging Face's logo

neuralmagic
/
oBERT-6-upstream-pretrained-dense

Transformers
PyTorch
English
bert
oBERT
sparsity
pruning
compression
Inference Endpoints
Model card Files Community
ekurtic commited on
Commit
8a6ae91
•
1 Parent(s): d75d5e3

Add link to code

Browse files
Files changed (1) hide show
  1. README.md +4 -2
README.md CHANGED
@@ -32,9 +32,11 @@ Sparsity: 0%
32
  Number of layers: 6
33
  ```
34
 
35
- Code: _coming soon_
36
 
37
- ## BibTeX entry and citation info
 
 
38
  ```bibtex
39
  @article{kurtic2022optimal,
40
  title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},
 
32
  Number of layers: 6
33
  ```
34
 
35
+ 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)
36
 
37
+ If you find the model useful, please consider citing our work.
38
+
39
+ ## Citation info
40
  ```bibtex
41
  @article{kurtic2022optimal,
42
  title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},