Lapisbird

/

Llama-adaLR-model-latent-6-by-1

like 0

This PR enhances the model card by:

• Adding the pipeline_tag: text-generation for improved discoverability.
• Including a link to the paper: Learning When to Stop: Adaptive Latent Reasoning via Reinforcement Learning.
• Adding a link to the GitHub repository: https://github.com/apning/adaptive-latent-reasoning.
• Providing a sample code snippet for loading the model, extracted from the GitHub README.