Model release
Browse files- .gitattributes +1 -0
- README.md +40 -0
- all_results.json +3 -0
- config.json +3 -0
- eval_results.json +3 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +3 -0
- train_results.json +3 -0
- trainer_state.json +3 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
.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 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# oBERT-12-upstream-pruned-unstructured-97-finetuned-mnli-v2
|
2 |
+
|
3 |
+
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).
|
4 |
+
|
5 |
+
|
6 |
+
It corresponds to the model presented in the `Table 2 - oBERT - MNLI 97%` (in the upcoming updated version of the paper).
|
7 |
+
|
8 |
+
```
|
9 |
+
Pruning method: oBERT upstream unstructured + sparse-transfer to downstream
|
10 |
+
Paper: https://arxiv.org/abs/2203.07259
|
11 |
+
Dataset: MNLI
|
12 |
+
Sparsity: 97%
|
13 |
+
Number of layers: 12
|
14 |
+
```
|
15 |
+
|
16 |
+
The dev-set performance reported in the paper is averaged over four seeds, and we release the best model (marked with `(*)`):
|
17 |
+
|
18 |
+
```
|
19 |
+
| oBERT 97% | m-acc | mm-acc|
|
20 |
+
| ------------- | ----- | ----- |
|
21 |
+
| seed=42 | 80.86 | 80.88 |
|
22 |
+
| seed=3407 | 80.83 | 81.65 |
|
23 |
+
| seed=123 (*)| 81.18 | 81.06 |
|
24 |
+
| seed=12345 | 80.79 | 80.95 |
|
25 |
+
| ------------- | ----- | ----- |
|
26 |
+
| mean | 80.91 | 81.13 |
|
27 |
+
| stdev | 0.178 | 0.351 |
|
28 |
+
```
|
29 |
+
|
30 |
+
Code: _coming soon_
|
31 |
+
|
32 |
+
## BibTeX entry and citation info
|
33 |
+
```bibtex
|
34 |
+
@article{kurtic2022optimal,
|
35 |
+
title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},
|
36 |
+
author={Kurtic, Eldar and Campos, Daniel and Nguyen, Tuan and Frantar, Elias and Kurtz, Mark and Fineran, Benjamin and Goin, Michael and Alistarh, Dan},
|
37 |
+
journal={arXiv preprint arXiv:2203.07259},
|
38 |
+
year={2022}
|
39 |
+
}
|
40 |
+
```
|
all_results.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:129775b61b3b1d44878161d5e98c658a63a03618966b2460a3d39b7deeccfe91
|
3 |
+
size 657
|
config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8eaeb7d693e98ba0031a91263d6dcb17eabd9aeab210560f1c05734326765968
|
3 |
+
size 1028
|
eval_results.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dc4989c3a5ed7d577778a3dbbfa21e8bacdc72f30276ca138263f0902ba4348
|
3 |
+
size 479
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:469c97bd0037cad2d9716c140f281dc21bdf32f8a6a8cc106e9d43d48bc37591
|
3 |
+
size 438025197
|
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:da0e79933b9ed51798a3ae27893d3c5fa4a201126cef75586296df9b4d2c62a0
|
3 |
+
size 711661
|
tokenizer_config.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c6863d5eead8a7621fbfc9f434b9ad08693b40f7e17da33922dfb395a8645ca
|
3 |
+
size 392
|
train_results.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16ef4261c51becc4d18930b04949f7f15e3be762361d37063fd20993644869da
|
3 |
+
size 198
|
trainer_state.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:adc464875aee69fd04fd45164b20cdc50963d4fc8ddd420795e72d4b37ffef92
|
3 |
+
size 26496
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f71299b9048fe5f2c1b32267c10f33629a3505089438fec47f14997f17a74321
|
3 |
+
size 3375
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|