ABaroian

/

Apertus-8B-RLVR-GSM

like 2

This PR enhances the model card for rlvr_apertus-8b-grpo-gsm8k by:

• Updating the pipeline_tag from reinforcement-learning to text-generation to reflect the model's primary function, and moving reinforcement-learning into the general tags list.
• Adding library_name: transformers to enable the interactive inference widget, as the model is compatible with the transformers library (based on the config.json of the base model indicating LlamaForCausalLM architecture).
• Adding direct links to the official Hugging Face paper page, the project page, and the GitHub repository for easier access to relevant information.

These changes improve the model's discoverability and provide users with clearer and more comprehensive information.