XPSR on Hugging Face #5
Comments
|
Dear Niels:
Thank you very much and I am honored that you have shown interest in our paper. We are very interested in your suggestion to showcase the model and demo on the Huggingface website.
However, the authors have recently been busy with other visual research and do not have time to deal with these tasks. Is there a time limit for this matter? We are happy to upload the model and build the demo on Huggingface within approximately one or two months.
Thank you again for your attention and the contribution of Huggingface website to the open source community, which has been of great help to our research.
Yours Sincerely,
Yunpeng Qu
…------------------ 原始邮件 ------------------
发件人: "qyp2000/XPSR" ***@***.***>;
发送时间: 2024年9月28日(星期六) 晚上6:42
***@***.***>;
***@***.******@***.***>;
主题: [qyp2000/XPSR] XPSR on Hugging Face (Issue #5)
Hello @qyp2000 🤗
I'm Niels and I work on computer vision at Hugging Face. I see your paper is accepted as ECCV Poster, congratulations! I will index it here https://huggingface.co/papers/index?arxivId=2403.05049 at paper pages. The paper page lets people discuss about your paper and lets them find artifacts about it (your model for instance) you can also claim the paper as yours which will show up on your public profile at HF.
Would you like to host the model you've pre-trained with this technique on https://huggingface.co/models? I see you're using a Google Drive for it. Hosting on Hugging Face will give you more visibility. We can add tags in the model cards so that people find the models easier.
If you're down, leaving a guide here. If it's a PyTorch model, you can use PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to the model which lets you to upload the model and people to download and use models right away.
If you do not want this and directly want to upload model through UI or however you want, people can also use hf_hub_download.
After uploaded, we can also link the models and datasets to the paper page (read here) so people can discover your model.
You can also build a demo to your model on Spaces we can provide you an A100 grant.
What do you think?
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you were mentioned.Message ID: ***@***.***>
|
|
Hi @qyp2000 thanks for your reply! One or two months is fine. I could also send a PR if you could point to the main class of your model (if you're inheriting from pipelines in the Diffusers library, it's possible you already inherit the We just hope to make machine learning more collaborative, by allowing people to discover artifacts on https://huggingface.co/papers/2403.05049, have proper model cards with tags such as |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hello @qyp2000 🤗
I'm Niels and I work on computer vision at Hugging Face. I see your paper is accepted as ECCV Poster, congratulations! I will index it here https://huggingface.co/papers/index?arxivId=2403.05049 at paper pages. The paper page lets people discuss about your paper and lets them find artifacts about it (your model for instance) you can also claim the paper as yours which will show up on your public profile at HF.
Would you like to host the model you've pre-trained with this technique on https://huggingface.co/models? I see you're using a Google Drive for it. Hosting on Hugging Face will give you more visibility. We can add tags in the model cards so that people find the models easier.
If you're down, leaving a guide here. If it's a PyTorch model, you can use PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to the model which lets you to upload the model and people to download and use models right away.
If you do not want this and directly want to upload model through UI or however you want, people can also use hf_hub_download.
After uploaded, we can also link the models and datasets to the paper page (read here) so people can discover your model.
You can also build a demo to your model on Spaces we can provide you an A100 grant.
What do you think?
The text was updated successfully, but these errors were encountered: