up

README.md

@@ -57,9 +57,13 @@ We also check the performance of bi-encoders using the same evaluation: The retr
 | [cross-encoder/msmarco-MiniLM-L6-en-de-v1](https://huggingface.co/cross-encoder/msmarco-MiniLM-L6-en-de-v1) | 72.43 | 65.53 | 46.77 | 1600 |
 | [cross-encoder/msmarco-MiniLM-L12-en-de-v1](https://huggingface.co/cross-encoder/msmarco-MiniLM-L12-en-de-v1) | 72.94 | 66.07 | 49.91 | 900 |
 | [svalabs/cross-electra-ms-marco-german-uncased](https://huggingface.co/svalabs/cross-electra-ms-marco-german-uncased) (DE only) | - | - | 53.67 | 260 |
+| [deepset/gbert-base-germandpr-reranking](https://huggingface.co/deepset/gbert-base-germandpr-reranking) (DE only) | - | - | 53.59 | 260 |
 | **Bi-Encoders (re-ranking)** | | | |
 | [sentence-transformers/msmarco-distilbert-multilingual-en-de-v2-tmp-lng-aligned](https://huggingface.co/sentence-transformers/msmarco-distilbert-multilingual-en-de-v2-tmp-lng-aligned) | 63.38 | 58.28 | 37.88 | 940 |
 | [sentence-transformers/msmarco-distilbert-multilingual-en-de-v2-tmp-trained-scratch](https://huggingface.co/sentence-transformers/msmarco-distilbert-multilingual-en-de-v2-tmp-trained-scratch) | 65.51 | 58.69 | 38.32 | 940 |
 | [svalabs/bi-electra-ms-marco-german-uncased](https://huggingface.co/svalabs/bi-electra-ms-marco-german-uncased) (DE only) | - | - | 34.31 | 450 |
+| [deepset/gbert-base-germandpr-question_encoder](https://huggingface.co/deepset/gbert-base-germandpr-question_encoder) (DE only) | - | - | 42.55 | 450 |
+
+
 
  Note: Docs / Sec gives the number of (query, document) pairs we can re-rank within a second on a V100 GPU.