Release fine-tuned models from "Refining Text Generation" on Hugging Face

[NielsRogge]

Hi @UEC-InabaLab 🤗

Niels here from the open-source team at Hugging Face. I discovered your work on Arxiv and was wondering whether you would like to submit it to hf.co/papers to improve its discoverability. If you are one of the authors, you can submit it at https://huggingface.co/papers/submit.

Your paper, "Refining Text Generation for Realistic Conversational Recommendation via Direct Preference Optimization", introduces a compelling method for fine-tuning LLMs for conversational recommendation. It'd be great to make the fine-tuned model checkpoints (e.g., your DPO-trained summary generation and recommendation generation models, and the fine-tuned DeBERTa score predictor) available on the 🤗 Hub, to improve their discoverability/visibility. We can add tags so that people find them when filtering https://huggingface.co/models.

We noticed that while your code is publicly available on GitHub, the specific fine-tuned checkpoints are generated locally. Hosting these directly on the Hub would allow others to easily load and experiment with your models without needing to run the full training process themselves, like so:

from transformers import AutoModelForCausalLM

model = AutoModelForCausalLM.from_pretrained("your-hf-org-or-username/your-model")

Uploading models

See here for a guide: https://huggingface.co/docs/hub/models-uploading.

In this case, 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 (e.g., each of your fine-tuned components) 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 can also build a demo for your models 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 regarding this!

Cheers,

Niels
ML Engineer @ HF 🤗