Update README.md
Browse files
README.md
CHANGED
@@ -7,24 +7,28 @@ widget:
|
|
7 |
- text: Rigtig god service!
|
8 |
---
|
9 |
|
10 |
-
|
|
|
|
|
11 |
|
12 |
The model uses 5 classes ranging from 1-5 stars:
|
13 |
|
14 |
-
* ⭐ (poor)
|
15 |
-
* ⭐⭐
|
16 |
-
* ⭐⭐⭐
|
17 |
-
* ⭐⭐⭐⭐
|
18 |
* ⭐⭐⭐⭐⭐ (very good)
|
19 |
|
20 |
-
The model is fine-tuned using
|
|
|
|
|
21 |
|
22 |
Test the model using the [🤗Transformers](https://github.com/huggingface/transformers) library pipeline:
|
23 |
|
24 |
```python
|
25 |
from transformers import pipeline
|
26 |
|
27 |
-
classifier = pipeline("sentiment-analysis", model="danish-bert-review-sentiment")
|
28 |
classifier("Intet virkede og ingen hjælp at hente.")
|
29 |
|
30 |
#[{'label': '⭐', 'score': 0.4953940808773041}]
|
@@ -35,6 +39,6 @@ Or load it using the Auto* classes:
|
|
35 |
```python
|
36 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
37 |
|
38 |
-
model = AutoModelForSequenceClassification.from_pretrained("danish-bert-review-sentiment")
|
39 |
-
tokenizer = AutoTokenizer.from_pretrained("danish-bert-review-sentiment")
|
40 |
```
|
|
|
7 |
- text: Rigtig god service!
|
8 |
---
|
9 |
|
10 |
+
# What is this?
|
11 |
+
|
12 |
+
BERT classification model for short customer reviews written in Danish.
|
13 |
|
14 |
The model uses 5 classes ranging from 1-5 stars:
|
15 |
|
16 |
+
* ⭐ (very poor)
|
17 |
+
* ⭐⭐ (poor)
|
18 |
+
* ⭐⭐⭐ (neutral)
|
19 |
+
* ⭐⭐⭐⭐ (good)
|
20 |
* ⭐⭐⭐⭐⭐ (very good)
|
21 |
|
22 |
+
The model is fine-tuned using the pre-trained [Danish BERT model]("Maltehb/danish-bert-botxo").
|
23 |
+
|
24 |
+
# How to use
|
25 |
|
26 |
Test the model using the [🤗Transformers](https://github.com/huggingface/transformers) library pipeline:
|
27 |
|
28 |
```python
|
29 |
from transformers import pipeline
|
30 |
|
31 |
+
classifier = pipeline("sentiment-analysis", model="KennethTM/danish-bert-review-sentiment")
|
32 |
classifier("Intet virkede og ingen hjælp at hente.")
|
33 |
|
34 |
#[{'label': '⭐', 'score': 0.4953940808773041}]
|
|
|
39 |
```python
|
40 |
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
41 |
|
42 |
+
model = AutoModelForSequenceClassification.from_pretrained("KennethTM/danish-bert-review-sentiment")
|
43 |
+
tokenizer = AutoTokenizer.from_pretrained("KennethTM/danish-bert-review-sentiment")
|
44 |
```
|