Request for TQA-Bench Dataset #1
Description
Dear authors,
Thank you for your excellent research and for sharing your work with the community.
I would like to ask if it’s possible to obtain the TQA-Bench dataset in a readily usable format — specifically as a HuggingFace dataset or as a .json file.
While experimenting with the Qwen codebase on the 64k setting, I noticed that only about 1/20th of the full test set appears to be used.
To run more comprehensive evaluations, it would be very helpful to have access to the full dataset in plain text format.
Would it be possible to share the dataset in such a format?
Thank you again for your contributions.