Hi @ionutmodo 🤗
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/2605.07850.
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, add Github and project page URLs.
I noticed on your GitHub repository that you are planning to release the code and artifacts on May 11th. When the code is ready, would you like to host the hierarchical LoRA adapters you've trained on https://huggingface.co/models?
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 researchers can easily find and filter for MatryoshkaLoRA-trained adapters. Since your framework produces adapters that are compatible with the PEFT ecosystem, users can easily download and use them via the peft or transformers libraries.
If you're down, leaving a guide here. For PEFT adapters, it is very straightforward to use the push_to_hub method to make them available for the community to use right away.
After they are uploaded, we can also link the models to the paper page (read here) so people can discover your work more easily.
Let me know if you're interested or if you need any guidance when the release date approaches!
Kind regards,
Niels
Hi @ionutmodo 🤗
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/2605.07850.
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, add Github and project page URLs.
I noticed on your GitHub repository that you are planning to release the code and artifacts on May 11th. When the code is ready, would you like to host the hierarchical LoRA adapters you've trained on https://huggingface.co/models?
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 researchers can easily find and filter for MatryoshkaLoRA-trained adapters. Since your framework produces adapters that are compatible with the PEFT ecosystem, users can easily download and use them via the
peftortransformerslibraries.If you're down, leaving a guide here. For PEFT adapters, it is very straightforward to use the
push_to_hubmethod to make them available for the community to use right away.After they are uploaded, we can also link the models to the paper page (read here) so people can discover your work more easily.
Let me know if you're interested or if you need any guidance when the release date approaches!
Kind regards,
Niels