Skip to content

Conversation

@yusun-nlp
Copy link
Contributor

Motivation

Add evaluation configs, classes and functions for SciReasoner benchmark.

Modification

Added the evaluation configs python file, and datasets file. Also add a eval config, including dataset and summarizer for better understanding.

Notes

Have to download datasets from https://huggingface.co/collections/SciReason/evaluation-data, and replace all "/path/" with "/the-dir-of-eval-data"

@Myhs-phz Myhs-phz force-pushed the scireasoner branch 2 times, most recently from 6d2d3aa to 5492e7a Compare December 15, 2025 08:57
@Myhs-phz Myhs-phz closed this Dec 15, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants