Safetensors
qwen2

Update model card with metadata, links, and detailed description

#1
by nielsr HF Staff - opened

Hi! I'm Niels from the Hugging Face community team. This PR aims to significantly improve the model card for daVinci-origin-3B by adding comprehensive metadata and essential contextual information.

Specifically, this update includes:

  • Metadata: Adding pipeline_tag: text-generation for correct categorization and library_name: transformers to enable the automated code snippet widget, based on the model's Qwen2ForCausalLM architecture and transformers_version in its config files. Relevant tags have also been added for improved discoverability.
  • Project Resources: Providing clear links to the associated research paper (Data Darwinism Part I: Unlocking the Value of Scientific Data for Pre-training), the official GitHub repository, and other related Hugging Face artifacts.
  • Model Description: Expanding the model description with details from the paper abstract and GitHub README, including an overview of the "Data Darwinism Hierarchy" to better explain the model's scientific context and purpose.
  • Citation: Adding the official BibTeX citation for proper attribution.

These improvements will help users better understand, find, and utilize this valuable model.

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment