cccczshao

/

CALM-Autoencoder

like 8

This PR improves the model card by:

• Adding the pipeline_tag: text-generation to correctly categorize the model and enable its discoverability on the Hugging Face Hub. This tag is well-supported by the paper's abstract and model description.
• The library_name remains CALM. Although the config.json references a transformers_version, the model architecture (Autoencoder) and common usage patterns (often requiring trust_remote_code=True) suggest that it may not be fully natively integrated with the standard transformers auto-loading mechanism for the automated "how to use" widget. Retaining CALM avoids a potentially broken default code snippet.
• No sample usage section is added, as the provided GitHub README content does not contain an explicit Python code snippet for inference, following the strict guidelines.

Please review and merge if these changes are appropriate.