efederici commited on
Commit
eda417f
1 Parent(s): 71f734f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +8 -21
README.md CHANGED
@@ -12,13 +12,10 @@ datasets:
12
  - ARTeLab/fanpage
13
  ---
14
 
15
- <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
- should probably proofread and complete it, then remove this comment. -->
17
-
18
  # summarization_fanpage128
19
 
20
  This model is a fine-tuned version of [gsarti/it5-base](https://huggingface.co/gsarti/it5-base) on Fanpage dataset.
21
- It achieves the following results on the evaluation set:
22
  - Loss: 1.5492
23
  - Rouge1: 33.8286
24
  - Rouge2: 15.4551
@@ -26,19 +23,13 @@ It achieves the following results on the evaluation set:
26
  - Rougelsum: 28.3133
27
  - Gen Len: 69.7954
28
 
29
- ## Model description
30
-
31
- More information needed
32
-
33
- ## Intended uses & limitations
34
-
35
- More information needed
36
-
37
- ## Training and evaluation data
38
 
39
- More information needed
40
-
41
- ## Training procedure
 
 
42
 
43
  ### Training hyperparameters
44
 
@@ -51,13 +42,9 @@ The following hyperparameters were used during training:
51
  - lr_scheduler_type: linear
52
  - num_epochs: 4.0
53
 
54
- ### Training results
55
-
56
-
57
-
58
  ### Framework versions
59
 
60
  - Transformers 4.12.0.dev0
61
  - Pytorch 1.9.1+cu102
62
  - Datasets 1.12.1
63
- - Tokenizers 0.10.3
 
12
  - ARTeLab/fanpage
13
  ---
14
 
 
 
 
15
  # summarization_fanpage128
16
 
17
  This model is a fine-tuned version of [gsarti/it5-base](https://huggingface.co/gsarti/it5-base) on Fanpage dataset.
18
+ It achieves the following results:
19
  - Loss: 1.5492
20
  - Rouge1: 33.8286
21
  - Rouge2: 15.4551
 
23
  - Rougelsum: 28.3133
24
  - Gen Len: 69.7954
25
 
26
+ ## Usage
 
 
 
 
 
 
 
 
27
 
28
+ ```python
29
+ from transformers import T5Tokenizer, T5ForConditionalGeneration
30
+ tokenizer = T5Tokenizer.from_pretrained("ARTeLab/it5-summarization-fanpage-128")
31
+ model = T5ForConditionalGeneration.from_pretrained("ARTeLab/it5-summarization-fanpage-128")
32
+ ```
33
 
34
  ### Training hyperparameters
35
 
 
42
  - lr_scheduler_type: linear
43
  - num_epochs: 4.0
44
 
 
 
 
 
45
  ### Framework versions
46
 
47
  - Transformers 4.12.0.dev0
48
  - Pytorch 1.9.1+cu102
49
  - Datasets 1.12.1
50
+ - Tokenizers 0.10.3