Add ExtractBench evaluation results
#4
by boyang-runllama - opened
This PR ensures your model shows up at https://huggingface.co/datasets/llamaindex/ExtractBench.
This is based on the new evaluation results feature: https://huggingface.co/docs/hub/eval-results.
Note: this includes unified value F1 on each of the 3 ExtractBench length splits (short, medium, long) along with the overall mean score over all 370 documents.
Alexandre-Numind changed pull request status to merged