skeimSVA commited on
Commit
108bc90
1 Parent(s): 94f469c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -0
README.md CHANGED
@@ -1,3 +1,35 @@
1
  ---
2
  license: cc-by-4.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: cc-by-4.0
3
+ language:
4
+ - de
5
+ task_categories:
6
+ - question-answering
7
+ tags:
8
+ - question-answering
9
+ - pytorch
10
+ - qa
11
+ - de
12
  ---
13
+
14
+ # SVALabs - InfoXLM German QA
15
+
16
+ In this repository we present our german question answering model.
17
+
18
+ The trained model is based on [InfoXLM-large](https://huggingface.co/microsoft/infoxlm-large) and was finetuned using the [SQuAD](https://huggingface.co/datasets/squad) dataset and the [GermanQuAD](https://huggingface.co/datasets/deepset/germanquad) dataset.
19
+
20
+ ### Model Details
21
+
22
+ | | Description or Link |
23
+ |---|---|
24
+ |**Base model** | [```InfoXLM-large```](https://huggingface.co/microsoft/infoxlm-large) |
25
+ |**Finetuning task**| Question Answering |
26
+ |**Source datasets**| [```SQuAD```](https://huggingface.co/datasets/squad); [```GermanQuAD```](https://huggingface.co/datasets/deepset/germanquad)|
27
+
28
+
29
+ ### Performance
30
+
31
+ The model was tested on 1692 samples of the GermanQuAD test dataset (the other samples were used for validation)
32
+
33
+ F1-Score: 89.05
34
+
35
+ EM: 74.76