We're hosting a demo here for "A Watermark for Large Language Models" and we're wondering whether it would be possible to get some GPU assistance? We'd also love to see about hosting the bigger models like OPT-6.7b which might require an A100 card.
Hi @jwkirchenbauer, we have assigned a gpu to this space. Note that GPU Grants are provided temporarily and might be removed after some time if the usage is very low.
To learn more about GPUs in Spaces, please check out https://huggingface.co/docs/hub/spaces-gpus