Update README.md
Browse files
README.md
CHANGED
|
@@ -405,3 +405,10 @@ Evaluation on the [PIRB](https://huggingface.co/spaces/sdadas/pirb) benchmark de
|
|
| 405 |
</table>
|
| 406 |
|
| 407 |
Table 3. Comparison between two rerankers based on **polish-roberta-large-v2** and **polish-roberta-8k** on selected long-context tasks from the PIRB benchmark. We report absolute improvement of NDCG@10 score.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 405 |
</table>
|
| 406 |
|
| 407 |
Table 3. Comparison between two rerankers based on **polish-roberta-large-v2** and **polish-roberta-8k** on selected long-context tasks from the PIRB benchmark. We report absolute improvement of NDCG@10 score.
|
| 408 |
+
|
| 409 |
+
## Evaluation - Reranking for RAG
|
| 410 |
+
This project is financed by the European Funds, registered under the number FENG.01.01-IP.01-A028/23-00. It focuses on "Building innovative large language models and a service platform for serving multi-task models within the Bank."
|
| 411 |
+
The outcomes of this project are the result of a collaboration between the AI Lab at the National Information Processing Institute (Ośrodek Przetwarzania Informacji Państwowy Instytut Badawczy) and the AI Team at PKO Bank Polski.
|
| 412 |
+
|
| 413 |
+
Funding Amount by the European Funds: 9,2 mln PLN
|
| 414 |
+
|