PKOBP
/

polish-roberta-8k

Model card Files Files and versions

pabloQli commited on Jul 28

Commit

08f172f

·

verified ·

1 Parent(s): daa32f5

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -406,7 +406,7 @@ Evaluation on the [PIRB](https://huggingface.co/spaces/sdadas/pirb) benchmark de
 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.
-## Evaluation - Reranking for RAG
 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."
 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.

 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.
+## Acknowledgements
 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."
 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.