Hi @jh27kim 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2605.23346.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance), you can also claim the paper as yours which will show up on your public profile at HF, and add Github and project page URLs.
I see you have a Github repository for CDM, though it looks like the implementation and pre-trained checkpoints aren't available yet. Would you like to host the twist function checkpoints you've trained (for tasks like toxic text generation, DNA design, and protein designability) on https://huggingface.co/models when you are ready to release them?
Hosting on Hugging Face will give your work more visibility and enable better discoverability. We can add metadata tags to the model cards so that people find the models easier (especially for specialized tasks in biology and NLP), link them to the paper page, and provide download stats.
If you're interested, you can use the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to custom PyTorch models, allowing people to download and use your work with just a few lines of code.
Let me know if you're interested or need any guidance!
Kind regards,
Niels
Hi @jh27kim 🤗
I'm Niels and work as part of the open-source team at Hugging Face. I discovered your work through Hugging Face's daily papers as yours got featured: https://huggingface.co/papers/2605.23346.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models for instance), you can also claim the paper as yours which will show up on your public profile at HF, and add Github and project page URLs.
I see you have a Github repository for CDM, though it looks like the implementation and pre-trained checkpoints aren't available yet. Would you like to host the twist function checkpoints you've trained (for tasks like toxic text generation, DNA design, and protein designability) on https://huggingface.co/models when you are ready to release them?
Hosting on Hugging Face will give your work more visibility and enable better discoverability. We can add metadata tags to the model cards so that people find the models easier (especially for specialized tasks in biology and NLP), link them to the paper page, and provide download stats.
If you're interested, you can use the PyTorchModelHubMixin class which adds
from_pretrainedandpush_to_hubto custom PyTorch models, allowing people to download and use your work with just a few lines of code.Let me know if you're interested or need any guidance!
Kind regards,
Niels