Make dataset discoverable on HF

[NielsRogge]

Hi there,

Congrats on releasing the paper and dataset! Niels here from the open-source team at Hugging Face. I was wondering whether you would be up for making your dataset as a dedicated dataset repository, rather than adding them as part of the model repo. This way, people can do:

from datasets import load_dataset

dataset = load_dataset("qcznlp/uncertainty-attack")

? This would also ensure a dataset viewer, which allows people to easily discover and read the first few rows of the dataset in the browser. See here for a guide: https://huggingface.co/docs/datasets/loading.

Moreover, it could be linked to the paper: https://huggingface.co/papers/2407.11282, see here on how to do that: https://huggingface.co/docs/hub/en/datasets-cards#linking-a-paper.

Let me know if you need any help!

Cheers,

Niels
ML @ HF

[qcznlp]

Hi Niels,

Thanks for the suggestion! We will upload our datasets early next week.

Qingcheng

[NielsRogge]

Hi,

I just saw that the dataset is already on the hub, so I opened a PR to link it to the paper: https://huggingface.co/datasets/ErikYip/LLM-Uncertainty-Bench/discussions/1.

Would be great if you could merge it :)

Thanks,
Niels