Hugging Face's logo

deepset
/
gelectra-base-germanquad

Question Answering
Transformers
PyTorch
TensorFlow
Safetensors
German
electra
exbert
Model card Files
xet
 Community
3
sjrhuschlee commited on
Commit
7cd7dcc
·
1 Parent(s): 96a4f20

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -38,7 +38,7 @@ embeds_dropout_prob = 0.1
38
  We evaluated the extractive question answering performance on our GermanQuAD test set.
39
  Model types and training data are included in the model name.
40
  For finetuning XLM-Roberta, we use the English SQuAD v2.0 dataset.
41
- The GELECTRA models are warm started on the German translation of SQuAD v1.1 and finetuned on \\\\germanquad.
42
  The human baseline was computed for the 3-way test set by taking one answer as prediction and the other two as ground truth.
43
  ![performancetable](https://images.prismic.io/deepset/1c63afd8-40e6-4fd9-85c4-0dbb81996183_german-qa-vs-xlm-r.png)
44
 
 
38
  We evaluated the extractive question answering performance on our GermanQuAD test set.
39
  Model types and training data are included in the model name.
40
  For finetuning XLM-Roberta, we use the English SQuAD v2.0 dataset.
41
+ The GELECTRA models are warm started on the German translation of SQuAD v1.1 and finetuned on [GermanQuAD](https://deepset.ai/germanquad).
42
  The human baseline was computed for the 3-way test set by taking one answer as prediction and the other two as ground truth.
43
  ![performancetable](https://images.prismic.io/deepset/1c63afd8-40e6-4fd9-85c4-0dbb81996183_german-qa-vs-xlm-r.png)
44