Release MapCoder-Lite artifacts (models, dataset) on Hugging Face

[NielsRogge]

Hi @WoongQ 🤗

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/2509.17489.

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.

It'd be great to make the checkpoints (the specialized LoRA adapters for Retrieval, Planning, Coding, and Debugging) and the distilled trajectory datasets available on the 🤗 hub, to improve their discoverability/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 using LoRA adapters, you can easily push them using the peft library or the PyTorchModelHubMixin class. We encourage researchers to push each adapter to a separate model repository, so that things like download stats also work. We can then also link the checkpoints to the paper page.

Uploading dataset

I noticed "Dataset Extraction: TBD" in your README. It would be awesome to make those distilled trajectory datasets available on 🤗 , so that people can do:

from datasets import load_dataset

dataset = load_dataset("your-hf-org-or-username/your-dataset")

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 first few rows of the data in the browser.

Let me know if you're interested/need any help regarding this!

Cheers,

Niels
ML Engineer @ HF 🤗