OpenMOSE

/

HRWKV7-Reka-Flash3.1-Preview

like 1

This PR significantly improves the model card for HRWKV7-Reka-Flash3.1-Preview by:

• Adding essential metadata: pipeline_tag: text-generation, library_name: transformers, and comprehensive tags (rwkv, linear-attention, reka, distillation, knowledge-distillation, hybrid-architecture, language-model). This enhances discoverability and enables the "how to use" widget on the Hub.
• Adding the paper abstract for better context on the model's development via the RADLADS protocol.
• Updating the paper link to the official Hugging Face Papers page: RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale.
• Adding direct links to the main RADLADS project GitHub repository (https://github.com/recursal/RADLADS) and clarifying the link to this model's specific training code (https://github.com/OpenMOSE/RWKVInside).
• Replacing the non-standard curl usage snippet with a clear Python code example using the Hugging Face transformers library for easy model loading and generation.
• Adding the paper's BibTeX citation for proper attribution.

Please review and merge this PR if everything looks good.