Update README.md

This XLMR model was initialized from https://huggingface.co/deepset/xlm-roberta-base-squad2

The model was fine-tuned on machine-translated SQuAD v1.1 versions in Polish, Bulgarian, Czech and Romanian.


Results on test sets:

| Metric | bg | pl | cz | ro |
| -------|------|------|-------|-----|
|Exact match| 51.8 | 48.9 | 63.8 | 66.1 |
| f1 | 69 | 66.6 | 76.8 | 81.3 |

README.md

@@ -1,3 +1,10 @@
 ---
 license: creativeml-openrail-m
----
+datasets:
+- squad
+language:
+- bg
+- cs
+- ro
+- pl
+---