Update README.md
Browse files
README.md
CHANGED
@@ -3,16 +3,22 @@ license: apache-2.0
|
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
6 |
-
- name:
|
7 |
results: []
|
|
|
|
|
|
|
|
|
|
|
8 |
---
|
9 |
|
10 |
-
|
11 |
-
probably proofread and complete it, then remove this comment. -->
|
12 |
|
13 |
-
|
|
|
|
|
|
|
14 |
|
15 |
-
This model is a fine-tuned version of [distilbert-base-german-cased](https://huggingface.co/distilbert-base-german-cased) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
- Train Loss: 0.4640
|
18 |
- Train Accuracy: 0.7744
|
@@ -20,19 +26,8 @@ It achieves the following results on the evaluation set:
|
|
20 |
- Validation Accuracy: 0.7937
|
21 |
- Epoch: 1
|
22 |
|
23 |
-
## Model description
|
24 |
-
|
25 |
-
More information needed
|
26 |
-
|
27 |
-
## Intended uses & limitations
|
28 |
-
|
29 |
-
More information needed
|
30 |
-
|
31 |
-
## Training and evaluation data
|
32 |
-
|
33 |
-
More information needed
|
34 |
-
|
35 |
## Training procedure
|
|
|
36 |
|
37 |
### Training hyperparameters
|
38 |
|
@@ -54,3 +49,7 @@ The following hyperparameters were used during training:
|
|
54 |
- TensorFlow 2.8.2
|
55 |
- Datasets 2.2.2
|
56 |
- Tokenizers 0.12.1
|
|
|
|
|
|
|
|
|
|
3 |
tags:
|
4 |
- generated_from_keras_callback
|
5 |
model-index:
|
6 |
+
- name: tmp3y468_8j
|
7 |
results: []
|
8 |
+
widget:
|
9 |
+
- text: "Ich liebe dich!"
|
10 |
+
example_title: "Non-vulgar"
|
11 |
+
- text: "Leck mich am arsch"
|
12 |
+
example_title: "Vulgar"
|
13 |
---
|
14 |
|
15 |
+
# KIZervus
|
|
|
16 |
|
17 |
+
This model is a fine-tuned version of [distilbert-base-german-cased](https://huggingface.co/distilbert-base-german-cased).
|
18 |
+
It is trained to classify german text into the classes "vulgar" speech and "non-vulgar" speech.
|
19 |
+
The data set is a collection of other labeled sources in german. For an overview, see the github repository here: https://github.com/NKDataConv/KIZervus
|
20 |
+
Both data and training procedure are documented in the GitHub repo. Your are welcome to contribute.
|
21 |
|
|
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Train Loss: 0.4640
|
24 |
- Train Accuracy: 0.7744
|
|
|
26 |
- Validation Accuracy: 0.7937
|
27 |
- Epoch: 1
|
28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
## Training procedure
|
30 |
+
For details, see the repo and documentation here: https://github.com/NKDataConv/KIZervus
|
31 |
|
32 |
### Training hyperparameters
|
33 |
|
|
|
49 |
- TensorFlow 2.8.2
|
50 |
- Datasets 2.2.2
|
51 |
- Tokenizers 0.12.1
|
52 |
+
|
53 |
+
### Supporter
|
54 |
+
|
55 |
+
![BMBF Logo](./BMBF_Logo.png)
|