Update README.md
Browse files
README.md
CHANGED
@@ -1,23 +1,28 @@
|
|
1 |
---
|
|
|
|
|
2 |
license: mit
|
3 |
datasets:
|
4 |
- cardiffnlp/super_tweeteval
|
5 |
-
language:
|
6 |
-
- en
|
7 |
pipeline_tag: text-classification
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
# cardiffnlp/twitter-roberta-large-emoji-latest
|
10 |
|
11 |
This is a RoBERTa-large model trained on 154M tweets until the end of December 2022 and finetuned for emoji classification (multiclass classification on 100 emojis) on the _TweetEmoji100_ dataset of [SuperTweetEval](https://huggingface.co/datasets/cardiffnlp/super_tweeteval).
|
12 |
-
The original Twitter-
|
13 |
|
14 |
## Example
|
15 |
```python
|
16 |
from transformers import pipeline
|
17 |
text= "I’m tired of being sick.. it’s been four days dawg"
|
18 |
|
19 |
-
pipe = pipeline('text-classification', model="cardiffnlp/twitter-roberta-large-emoji-latest")
|
20 |
-
pipe(text)
|
21 |
predictions = pipe(text)[0]
|
22 |
predictions = sorted(predictions, key=lambda d: d['score'], reverse=True)
|
23 |
predictions[:5]
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
license: mit
|
5 |
datasets:
|
6 |
- cardiffnlp/super_tweeteval
|
|
|
|
|
7 |
pipeline_tag: text-classification
|
8 |
+
inference:
|
9 |
+
parameters:
|
10 |
+
return_all_scores: True
|
11 |
+
widget:
|
12 |
+
- text: >-
|
13 |
+
I’m tired of being sick.. it’s been four days dawg
|
14 |
---
|
15 |
# cardiffnlp/twitter-roberta-large-emoji-latest
|
16 |
|
17 |
This is a RoBERTa-large model trained on 154M tweets until the end of December 2022 and finetuned for emoji classification (multiclass classification on 100 emojis) on the _TweetEmoji100_ dataset of [SuperTweetEval](https://huggingface.co/datasets/cardiffnlp/super_tweeteval).
|
18 |
+
The original Twitter-larged RoBERTa model can be found [here](https://huggingface.co/cardiffnlp/twitter-roberta-large-2022-154m).
|
19 |
|
20 |
## Example
|
21 |
```python
|
22 |
from transformers import pipeline
|
23 |
text= "I’m tired of being sick.. it’s been four days dawg"
|
24 |
|
25 |
+
pipe = pipeline('text-classification', model="cardiffnlp/twitter-roberta-large-emoji-latest", return_all_scores=True))
|
|
|
26 |
predictions = pipe(text)[0]
|
27 |
predictions = sorted(predictions, key=lambda d: d['score'], reverse=True)
|
28 |
predictions[:5]
|