Hello,
Niels here from the open-source team at Hugging Face. I discovered your work on AgentOPSD through Hugging Face Daily Papers: https://huggingface.co/papers/2608.05987
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 in the Github repository that the code is coming soon. Once the training code and scripts are released, it would be great to also make the trained checkpoints (e.g., the Qwen2.5-3B and Qwen2.5-7B models trained with AgentOPSD on ALFWorld, WebShop, and Search-QA) available on the 🤗 hub, to improve their discoverability/visibility.
We can add tags (e.g. reinforcement-learning) so that people find them when filtering https://huggingface.co/models.
Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
Since your models are Qwen2.5-based, they can be uploaded in a format directly compatible with the transformers library. For custom PyTorch models, you can use 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 so people can discover your work.
You can also build a demo for your model on Spaces. ZeroGPU gives on-demand GPU-backed compute for demo Spaces.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗
Hello,
Niels here from the open-source team at Hugging Face. I discovered your work on AgentOPSD through Hugging Face Daily Papers: https://huggingface.co/papers/2608.05987
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 in the Github repository that the code is coming soon. Once the training code and scripts are released, it would be great to also make the trained checkpoints (e.g., the Qwen2.5-3B and Qwen2.5-7B models trained with AgentOPSD on ALFWorld, WebShop, and Search-QA) available on the 🤗 hub, to improve their discoverability/visibility.
We can add tags (e.g.
reinforcement-learning) so that people find them when filtering https://huggingface.co/models.Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
Since your models are Qwen2.5-based, they can be uploaded in a format directly compatible with the
transformerslibrary. For custom PyTorch models, you can use the PyTorchModelHubMixin class which addsfrom_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 so people can discover your work.
You can also build a demo for your model on Spaces. ZeroGPU gives on-demand GPU-backed compute for demo Spaces.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗