philschmid HF staff commited on
Commit
d74f756
1 Parent(s): 03b04ae

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +31 -0
README.md ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language: en
3
+ tags:
4
+ - summarization
5
+ license: apache-2.0
6
+ datasets:
7
+ - cnn_dailymail
8
+ - xsum
9
+ thumbnail: https://huggingface.co/front/thumbnails/distilbart_medium.png
10
+ ---
11
+
12
+ # This is an Tensorflow fork of [sshleifer/distilbart-cnn-12-6](https://huggingface.co/sshleifer/distilbart-cnn-12-6)
13
+
14
+ ### Usage
15
+
16
+ This checkpoint should be loaded into `BartForConditionalGeneration.from_pretrained`. See the [BART docs](https://huggingface.co/transformers/model_doc/bart.html?#transformers.BartForConditionalGeneration) for more information.
17
+
18
+ ### Metrics for DistilBART models
19
+
20
+ | Model Name | MM Params | Inference Time (MS) | Speedup | Rouge 2 | Rouge-L |
21
+ |:---------------------------|------------:|----------------------:|----------:|----------:|----------:|
22
+ | distilbart-xsum-12-1 | 222 | 90 | 2.54 | 18.31 | 33.37 |
23
+ | distilbart-xsum-6-6 | 230 | 132 | 1.73 | 20.92 | 35.73 |
24
+ | distilbart-xsum-12-3 | 255 | 106 | 2.16 | 21.37 | 36.39 |
25
+ | distilbart-xsum-9-6 | 268 | 136 | 1.68 | 21.72 | 36.61 |
26
+ | bart-large-xsum (baseline) | 406 | 229 | 1 | 21.85 | 36.50 |
27
+ | distilbart-xsum-12-6 | 306 | 137 | 1.68 | 22.12 | 36.99 |
28
+ | bart-large-cnn (baseline) | 406 | 381 | 1 | 21.06 | 30.63 |
29
+ | distilbart-12-3-cnn | 255 | 214 | 1.78 | 20.57 | 30.00 |
30
+ | distilbart-12-6-cnn | 306 | 307 | 1.24 | 21.26 | 30.59 |
31
+ | distilbart-6-6-cnn | 230 | 182 | 2.09 | 20.17 | 29.70 |