Hi @monster119120 🤗
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/2606.01528.
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 README that the model and data releases are currently listed as "TBD". It'd be great to make the checkpoints (actor and compressor) and your new dataset of 24k interaction trajectories available on the 🤗 hub to improve their discoverability and visibility.
We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.
Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
In this case, since you are working with Qwen-VL based architectures, you could leverage the PyTorchModelHubMixin class or directly push the weights. We encourage researchers to push each model checkpoint to a separate model repository so that things like download stats and metadata tags work correctly.
Uploading dataset
Would be awesome to make the 24k sample interaction dataset available on 🤗 , so that people can do:
from datasets import load_dataset
dataset = load_dataset("MobileLLM/JAMEL-trajectories")See here for a guide: https://huggingface.co/docs/datasets/loading.
Besides that, there's the dataset viewer which allows people to quickly explore the trajectories and novelty signals in the browser.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗
Hi @monster119120 🤗
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/2606.01528.
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 README that the model and data releases are currently listed as "TBD". It'd be great to make the checkpoints (actor and compressor) and your new dataset of 24k interaction trajectories available on the 🤗 hub to improve their discoverability and visibility.
We can add tags so that people find them when filtering https://huggingface.co/models and https://huggingface.co/datasets.
Uploading models
See here for a guide: https://huggingface.co/docs/hub/models-uploading.
In this case, since you are working with Qwen-VL based architectures, you could leverage the PyTorchModelHubMixin class or directly push the weights. We encourage researchers to push each model checkpoint to a separate model repository so that things like download stats and metadata tags work correctly.
Uploading dataset
Would be awesome to make the 24k sample interaction dataset available on 🤗 , so that people can do:
See here for a guide: https://huggingface.co/docs/datasets/loading.
Besides that, there's the dataset viewer which allows people to quickly explore the trajectories and novelty signals in the browser.
Let me know if you're interested/need any help regarding this!
Cheers,
Niels
ML Engineer @ HF 🤗