Update README.md
Browse files
README.md
CHANGED
@@ -1,23 +1,22 @@
|
|
1 |
---
|
2 |
-
language:
|
3 |
-
- it_IT
|
4 |
-
- it_IT
|
5 |
tags:
|
6 |
-
-
|
|
|
|
|
7 |
metrics:
|
8 |
- rouge
|
9 |
model-index:
|
10 |
- name: summarization_mbart_ilpost
|
11 |
results: []
|
|
|
|
|
12 |
---
|
13 |
|
14 |
-
|
15 |
-
should probably proofread and complete it, then remove this comment. -->
|
16 |
|
17 |
-
|
18 |
|
19 |
-
|
20 |
-
It achieves the following results on the evaluation set:
|
21 |
- Loss: 2.3640
|
22 |
- Rouge1: 38.9101
|
23 |
- Rouge2: 21.384
|
@@ -25,19 +24,12 @@ It achieves the following results on the evaluation set:
|
|
25 |
- Rougelsum: 35.0743
|
26 |
- Gen Len: 39.8843
|
27 |
|
28 |
-
##
|
29 |
-
|
30 |
-
|
31 |
-
|
32 |
-
|
33 |
-
|
34 |
-
More information needed
|
35 |
-
|
36 |
-
## Training and evaluation data
|
37 |
-
|
38 |
-
More information needed
|
39 |
-
|
40 |
-
## Training procedure
|
41 |
|
42 |
### Training hyperparameters
|
43 |
|
@@ -50,13 +42,9 @@ The following hyperparameters were used during training:
|
|
50 |
- lr_scheduler_type: linear
|
51 |
- num_epochs: 4.0
|
52 |
|
53 |
-
### Training results
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
### Framework versions
|
58 |
|
59 |
- Transformers 4.15.0.dev0
|
60 |
- Pytorch 1.10.0+cu102
|
61 |
- Datasets 1.15.1
|
62 |
-
- Tokenizers 0.10.3
|
|
|
1 |
---
|
|
|
|
|
|
|
2 |
tags:
|
3 |
+
- summarization
|
4 |
+
language:
|
5 |
+
- it
|
6 |
metrics:
|
7 |
- rouge
|
8 |
model-index:
|
9 |
- name: summarization_mbart_ilpost
|
10 |
results: []
|
11 |
+
datasets:
|
12 |
+
- ARTeLab/ilpost
|
13 |
---
|
14 |
|
15 |
+
# mbart_summarization_ilpost
|
|
|
16 |
|
17 |
+
This model is a fine-tuned version of [facebook/mbart-large-cc25](https://huggingface.co/facebook/mbart-large-cc25) on IlPost dataset for Abstractive Summarization..
|
18 |
|
19 |
+
It achieves the following results:
|
|
|
20 |
- Loss: 2.3640
|
21 |
- Rouge1: 38.9101
|
22 |
- Rouge2: 21.384
|
|
|
24 |
- Rougelsum: 35.0743
|
25 |
- Gen Len: 39.8843
|
26 |
|
27 |
+
## Usage
|
28 |
+
```python
|
29 |
+
from transformers import MBartTokenizer, MBartForConditionalGeneration
|
30 |
+
tokenizer = MBartTokenizer.from_pretrained("ARTeLab/mbart-summarization-ilpost")
|
31 |
+
model = MBartForConditionalGeneration.from_pretrained("ARTeLab/mbart-summarization-ilpost")
|
32 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
33 |
|
34 |
### Training hyperparameters
|
35 |
|
|
|
42 |
- lr_scheduler_type: linear
|
43 |
- num_epochs: 4.0
|
44 |
|
|
|
|
|
|
|
|
|
45 |
### Framework versions
|
46 |
|
47 |
- Transformers 4.15.0.dev0
|
48 |
- Pytorch 1.10.0+cu102
|
49 |
- Datasets 1.15.1
|
50 |
+
- Tokenizers 0.10.3
|