ekurtic commited on
Commit
82c14c1
1 Parent(s): f2baa2a

Model release

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # MNLI teacher
2
+
3
+ This model is used as a teacher for all runs on the MNLI downstream task in the paper [The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models](https://arxiv.org/abs/2203.07259).
4
+
5
+ MNLI dev-set:
6
+ ```
7
+ matched accuracy = 84.54
8
+ mismatched accuracy = 85.06
9
+ ```
10
+
11
+ ## BibTeX entry and citation info
12
+ ```bibtex
13
+ @article{kurtic2022optimal,
14
+ title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},
15
+ author={Kurtic, Eldar and Campos, Daniel and Nguyen, Tuan and Frantar, Elias and Kurtz, Mark and Fineran, Benjamin and Goin, Michael and Alistarh, Dan},
16
+ journal={arXiv preprint arXiv:2203.07259},
17
+ year={2022}
18
+ }
19
+ ```
config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac6620fec7d226abd4b1c7e027563a5b4473cf6336f8e925394c41da5dc13bc8
3
+ size 856
eval_results.txt ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ matched accuracy = 0.8454
2
+ mm accuracy = 0.8506
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a52a807602101fa78fe52d835fbb47cc095df505b4fc5f761bf5775a266175b7
3
+ size 438022317
special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:303df45a03609e4ead04bc3dc1536d0ab19b5358db685b6f3da123d05ec200e3
3
+ size 112
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be50c3628f2bf5bb5e3a7f17b1f74611b2561a3a27eeab05e5aa30f411572037
3
+ size 466247
tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a863c20bb9664ba983f10e20d34c790e0eea92f165fc4716c4bad62f6bdc70b4
3
+ size 285
vocab.txt ADDED
The diff for this file is too large to render. See raw diff