oluwatosin adewumi
commited on
Commit
•
e87bb77
1
Parent(s):
b4f4823
README updated again
Browse files
README.md
CHANGED
@@ -4,20 +4,21 @@ language:
|
|
4 |
- en
|
5 |
license: cc-by-4.0
|
6 |
tags:
|
7 |
-
-
|
8 |
- transformers
|
9 |
datasets:
|
10 |
-
-
|
11 |
metrics:
|
12 |
-
-
|
13 |
widget:
|
14 |
-
|
15 |
---
|
16 |
|
17 |
## T5Base-PCL
|
18 |
This is a fine-tuned model of T5 (base) on the patronizing and condenscending language (PCL) dataset by Pérez-Almendros et al (2020) used for Task 4 competition of SemEval-2022.
|
19 |
-
It is intended to be used as a classification model for identifying PCL.
|
20 |
-
|
|
|
21 |
The macro F1 score achieved on the test set, based on the official evaluation, is 0.5452.
|
22 |
More information about the original pre-trained model can be found [here](https://huggingface.co/t5-base)
|
23 |
|
@@ -26,5 +27,6 @@ More information about the original pre-trained model can be found [here](https:
|
|
26 |
```python
|
27 |
from transformers import T5ForConditionalGeneration, T5Tokenizer
|
28 |
import torch
|
29 |
-
tokenizer =
|
30 |
-
model =
|
|
|
|
4 |
- en
|
5 |
license: cc-by-4.0
|
6 |
tags:
|
7 |
+
- text classification
|
8 |
- transformers
|
9 |
datasets:
|
10 |
+
- PCL
|
11 |
metrics:
|
12 |
+
- F1
|
13 |
widget:
|
14 |
-
|
15 |
---
|
16 |
|
17 |
## T5Base-PCL
|
18 |
This is a fine-tuned model of T5 (base) on the patronizing and condenscending language (PCL) dataset by Pérez-Almendros et al (2020) used for Task 4 competition of SemEval-2022.
|
19 |
+
It is intended to be used as a classification model for identifying PCL.
|
20 |
+
|
21 |
+
The dataset it's trained on is limited in scope, as it covers only some news texts covering about 20 English-speaking countries.
|
22 |
The macro F1 score achieved on the test set, based on the official evaluation, is 0.5452.
|
23 |
More information about the original pre-trained model can be found [here](https://huggingface.co/t5-base)
|
24 |
|
|
|
27 |
```python
|
28 |
from transformers import T5ForConditionalGeneration, T5Tokenizer
|
29 |
import torch
|
30 |
+
tokenizer = T5Tokenizer.from_pretrained("tosin/pcl_22")
|
31 |
+
model = T5ForConditionalGeneration.from_pretrained("tosin/pcl_22")
|
32 |
+
tokenizer.pad_token = tokenizer.eos_token
|