| # The finetuned LayoutXLm model on Czech dataset for Visual Question Answering | |
| The original model can be found [here](microsoft/layoutxlm-base) | |
| The CIVQA dataset is the Czech Invoice dataset for Visual Question Answering | |
| Achieved results: | |
| eval_answer_text_recall = 0.7065 | |
| eval_answer_text_f1 = 0.6998 | |
| eval_answer_text_precision = 0.7319 | |