[model_cards] Specify language meta + thumbnail

cc @tholor

see #2799
This commit is contained in:
Julien Chaumond
2020-02-10 11:20:05 -05:00
parent 125a75a121
commit 63a5399bc4

View File

@@ -1,3 +1,8 @@
---
language: german
thumbnail: https://thumb.tildacdn.com/tild3330-3735-4461-b133-656238643834/-/format/webp/deepset_performance.png
---
# German BERT # German BERT
## Overview ## Overview
@@ -33,7 +38,7 @@ During training we monitored the loss and evaluated different model checkpoints
- germEval18Fine: Macro f1 score for multiclass sentiment classification - germEval18Fine: Macro f1 score for multiclass sentiment classification
- germEval18coarse: Macro f1 score for binary sentiment classification - germEval18coarse: Macro f1 score for binary sentiment classification
- germEval14: Seq f1 score for NER (file names deuutf.*) - germEval14: Seq f1 score for NER (file names deuutf.\*)
- CONLL03: Seq f1 score for NER - CONLL03: Seq f1 score for NER
- 10kGNAD: Accuracy for document classification - 10kGNAD: Accuracy for document classification