Lapisbird

/

Llama-adaLR-appendix-model-meaned_codi

like 0

This PR enhances the model card by:

• Linking the model to its paper: Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning
• Adding a link to the official GitHub repository: https://github.com/apning/adaptive-latent-reasoning
• Including a pipeline_tag: text-generation in the metadata to improve discoverability on the Hugging Face Hub.
• Adding a sample usage snippet, including environment setup instructions, directly from the GitHub README to demonstrate how to load the model.
• Replacing the minimal "Built with Llama" with a more detailed description of the model.
• Removing the "File information" section, as it is internal context and not relevant for the public model card.

Please review and merge if everything looks good.