Improve model card: Add pipeline tag, correct base model, and add code/project links
#1
by
nielsr
HF Staff
- opened
This PR significantly improves the model card for Hermes 4 14B by:
- Adding
pipeline_tag: text-generationto the metadata: This correctly categorizes the model as a generative language model, improving its discoverability on the Hugging Face Hub (e.g., https://huggingface.co/models?pipeline_tag=text-generation). - Correcting
base_modelin metadata: Updatedbase_modelfromNousResearch/Hermes-4-14BtoQwen-3-14Bto accurately reflect that the model is based on Qwen 3 14B, as stated in its description. - Enhancing paper link: Added the official Hugging Face Papers link for the "Hermes 4 Technical Report" alongside the existing arXiv link, offering users more options to access the paper.
- Adding GitHub Repository link: Included a new "Code" section with a link to the official GitHub repository for Hermes 4 (
https://github.com/NousResearch/Hermes-4), providing easy access to the source code. - Adding dedicated Project Page section: Elevated the link to the Hermes 4 collection on Hugging Face to its own "Project Page" section for better visibility and navigation, and removed the redundant link from the "Quantized / Smaller Variants" section.
No changes were made to the existing transformers usage example as it is correct and valid.
Will changing the base_model break the model family tree? I want this model to show up as a quantization for Hermes like it currently does.
I think you can add multiple base models :)