Hugging Face's logo

ikim-uk-essen
/
geberta-large

Fill-Mask
Transformers
PyTorch
Safetensors
deberta-v2
Inference Endpoints
Model card Files Community
1
amindada commited on
Commit
1c1ea71
•
1 Parent(s): 96f630d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -56,10 +56,10 @@ The following table presents the F1 scores:
56
 
57
  | Model | [GE14](https://huggingface.co/datasets/germeval_14) | [GQuAD](https://huggingface.co/datasets/deepset/germanquad) | [GE18](https://huggingface.co/datasets/philschmid/germeval18) | TS | [GGP](https://github.com/JULIELab/GGPOnc) | GRAS<sup>1</sup> | [JS](https://github.com/JULIELab/jsyncc) | [DROC](https://gitlab2.informatik.uni-wuerzburg.de/kallimachos/DROC-Release) | Avg |
58
  |:---------------------:|:--------:|:----------:|:--------:|:--------:|:-------:|:------:|:--------:|:------:|:------:|
59
- | GBERT<sub>large</sub> | 88.48±0.23 | 81.51±0.84 | 54.37±1.65 | 73.60±0.61 | **79.17**±0.14 | 69.28±0.80 | 76.32±4.42 | 90.29±0.15 | 76.63±0.63 |
60
- | GELECTRA<sub>large</sub> | 88.39±0.13 | 80.51±0.41 | 55.41±1.54 | 73.84±0.86 | 79.09±0.09 | **70.16**±0.92 | 73.73±2.35 | 89.83±0.27 | 76.37±0.69 |
61
  | GeBERTa<sub>large</sub> | 88.84±0.18 | 82.52±0.59 | 53.76±1.86 | 75.32±0.53 | 78.35±0.08 | 70.02±1.34 | 82.16±2.36 | 90.39±0.24 | 77.67±0.69 |
62
- | GeBERTa<sub>xlarge</sub> | **89.04**±0.26 | **85.05**±0.63 | **55.80**±1.42 | **76.25**±0.704 | 76.71±0.08 | 67.92±1.00 | **82.42**±4.70 | **90.63**±0.21 | **77.98**±0.62 |
63
 
64
  <sup>1</sup>Is not published yet but is described in the [MedBERT.de paper](https://arxiv.org/abs/2303.08179).
65
 
 
56
 
57
  | Model | [GE14](https://huggingface.co/datasets/germeval_14) | [GQuAD](https://huggingface.co/datasets/deepset/germanquad) | [GE18](https://huggingface.co/datasets/philschmid/germeval18) | TS | [GGP](https://github.com/JULIELab/GGPOnc) | GRAS<sup>1</sup> | [JS](https://github.com/JULIELab/jsyncc) | [DROC](https://gitlab2.informatik.uni-wuerzburg.de/kallimachos/DROC-Release) | Avg |
58
  |:---------------------:|:--------:|:----------:|:--------:|:--------:|:-------:|:------:|:--------:|:------:|:------:|
59
+ | [GBERT](https://huggingface.co/deepset/gbert-large)<sub>large</sub> | 88.48±0.23 | 81.51±0.84 | 54.37±1.65 | 73.60±0.61 | **79.17**±0.14 | 69.28±0.80 | 76.32±4.42 | 90.29±0.15 | 76.63±0.63 |
60
+ | [GELECTRA](https://huggingface.co/deepset/gelectra-large)<sub>large</sub> | 88.39±0.13 | 80.51±0.41 | 55.41±1.54 | 73.84±0.86 | 79.09±0.09 | **70.16**±0.92 | 73.73±2.35 | 89.83±0.27 | 76.37±0.69 |
61
  | GeBERTa<sub>large</sub> | 88.84±0.18 | 82.52±0.59 | 53.76±1.86 | 75.32±0.53 | 78.35±0.08 | 70.02±1.34 | 82.16±2.36 | 90.39±0.24 | 77.67±0.69 |
62
+ | [GeBERTa](https://huggingface.co/ikim-uk-essen/geberta-xlarge)<sub>xlarge</sub> | **89.04**±0.26 | **85.05**±0.63 | **55.80**±1.42 | **76.25**±0.704 | 76.71±0.08 | 67.92±1.00 | **82.42**±4.70 | **90.63**±0.21 | **77.98**±0.62 |
63
 
64
  <sup>1</sup>Is not published yet but is described in the [MedBERT.de paper](https://arxiv.org/abs/2303.08179).
65