Hi @fangbozhen 馃
Niels here from 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/2508.09138.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo 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 in your GitHub repository's "馃毄 Plan" section that you're planning to release the source code for "Temporal Self-Consistency Voting" and "Temporal Consistency Reinforcement". That's great!
It would be fantastic to see your code released and, if you plan to share any fine-tuned model checkpoints (e.g., LLaDA models enhanced with your methods), to host them on the 馃 Hub. This would greatly improve their discoverability and visibility within the AI community. We can add tags so that people find them when filtering https://huggingface.co/models.
Uploading models (when ready)
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
If you release fine-tuned versions of models like LLaDA-8B-Instruct or LLaDA-1.5, we could leverage the PyTorchModelHubMixin class which adds from_pretrained and push_to_hub to any custom nn.Module. Alternatively, one can leverage the hf_hub_download one-liner to download a checkpoint from the hub.
We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.
You could also consider building a demo for your methods on Spaces, we can provide you a ZeroGPU grant, which gives you A100 GPUs for free.
Let me know if you're interested/need any guidance, once your code is released!
Cheers,
Niels
ML Engineer @ HF 馃
Hi @fangbozhen 馃
Niels here from 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/2508.09138.
The paper page lets people discuss about your paper and lets them find artifacts about it (your models, datasets or demo 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 in your GitHub repository's "馃毄 Plan" section that you're planning to release the source code for "Temporal Self-Consistency Voting" and "Temporal Consistency Reinforcement". That's great!
It would be fantastic to see your code released and, if you plan to share any fine-tuned model checkpoints (e.g., LLaDA models enhanced with your methods), to host them on the 馃 Hub. This would greatly improve their discoverability and visibility within the AI community. We can add tags so that people find them when filtering https://huggingface.co/models.
Uploading models (when ready)
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
If you release fine-tuned versions of models like LLaDA-8B-Instruct or LLaDA-1.5, we could leverage the PyTorchModelHubMixin class which adds
from_pretrainedandpush_to_hubto any customnn.Module. Alternatively, one can leverage the hf_hub_download one-liner to download a checkpoint from the hub.We encourage researchers to push each model checkpoint to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.
You could also consider building a demo for your methods on Spaces, we can provide you a ZeroGPU grant, which gives you A100 GPUs for free.
Let me know if you're interested/need any guidance, once your code is released!
Cheers,
Niels
ML Engineer @ HF 馃