Ko-VDR Train Public
Collection
Training Dataset for Korean Visual Document Retrieval • 4 items • Updated
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
KoVidore V1 (NDCG@5)
| Task | NDCG@5 |
|---|---|
| KoVidoreFinOCRRetrieval | 0.8225 |
| KoVidoreMIRRetrieval | 0.6359 |
| KoVidoreOfficeRetrieval | 0.8025 |
| KoVidoreSlideRetrieval | 0.7726 |
| KoVidoreVQARetrieval | 0.8721 |
| Average | 0.7811 |
KoVidore V2 (NDCG@10)
| Task | NDCG@10 |
|---|---|
| KoVidore2CybersecurityRetrieval | 0.7329 |
| KoVidore2EconomicRetrieval | 0.2441 |
| KoVidore2EnergyRetrieval | 0.6134 |
| KoVidore2HrRetrieval | 0.3271 |
| Average | 0.4793 |
- Downloads last month
- 51
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support