YirongSun

/

LLaSO-Base-3.8B-Instruct

like 0

This PR significantly enhances the model card for LLaSO-Base-3.8B-Instruct, a foundational model from the LLaSO framework for Large Language and Speech Models.

Key improvements include:

• Adding the pipeline_tag: audio-text-to-text, making the model discoverable in relevant searches on the Hugging Face Hub (e.g., https://huggingface.co/models?pipeline_tag=audio-text-to-text).
• Specifying library_name: transformers, which enables the automated "how to use" widget on the model page with a standard transformers code snippet.
• Including the language: en tag, as indicated in the model's configuration.
• Linking the model to its official paper: LLaSO: A Foundational Framework for Reproducible Research in Large Language and Speech Model.
• Providing explicit links to the associated datasets (LLaSO-Align, LLaSO-Instruct, LLaSO-Eval) in the metadata and content.
• Adding a comprehensive overview of the LLaSO framework and the LLaSO-Base model's key features, adapted from the original GitHub repository.
• Including a practical code example for inference using the transformers library, which is directly compatible with the automated widget.
• Linking to the official GitHub repository for further details and code.

Please review these additions for accuracy and completeness.