Michael4933

/

CapImagine-7B

like 0

Hi! I'm Niels from the Hugging Face community team. I'm opening this PR to document the CapImagine-7B model card.

This PR:

• Adds metadata for pipeline_tag (image-text-to-text) and library_name (transformers).
• Identifies the base_model as Qwen/Qwen2.5-VL-7B-Instruct.
• Links the model to the research paper "Imagination Helps Visual Reasoning, But Not Yet in Latent Space" and the official GitHub repository.
• Provides a summary of the model's contribution and proper citation.