Improve model card: Add InfLLM-V2 paper details and comprehensive citations

#3
by nielsr HF Staff - opened

This PR improves the model card for MiniCPM4.1-8B by:

  • Updating the main title to reflect the model's foundation in the InfLLM-V2 framework.
  • Adding a prominent introductory sentence linking directly to the foundational paper "InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation".
  • Clarifying the navigation links by relabeling the existing "Technical Report" to "MiniCPM4 Technical Report" and adding a new distinct link for the "InfLLM-V2 Paper".
  • Updating the "What's New" section to explicitly mention the InfLLM-V2 framework in relation to the MiniCPM4.1 series.
  • Enhancing the "Citation" section to include both the foundational InfLLM-V2 paper and the existing MiniCPM4 technical report, ensuring all relevant research is easily citable.

These changes provide clearer context and more complete references for users and researchers.

Cannot merge
This branch has merge conflicts in the following files:
  • README.md

Sign up or log in to comment