Add ParseBench evaluation results
#37
by boyang-runllama - opened
This PR ensures your model shows up at https://huggingface.co/datasets/llamaindex/ParseBench.
This is based on the new evaluation results feature: https://huggingface.co/docs/hub/eval-results.
Note: this is the overall score (mean across all 5 ParseBench dimensions: text_content, text_formatting, layout, chart, table).
Closing in favor of an updated PR with per-dimension performance details.
boyang-runllama changed pull request status to closed