PaDT-MLLM

/

PaDT_RIC_3B

like 0

This PR enhances the model card by:

• Adding library_name: transformers to the metadata, which enables the automated "How to use" widget for inference with the Hugging Face transformers library. The model uses transformers.AutoProcessor and PaDTForConditionalGeneration.from_pretrained as shown in the sample usage.
• Including additional tags (multimodal-llm, object-detection, image-segmentation, referring-expression-comprehension, image-captioning) to improve discoverability, reflecting the diverse vision tasks the model supports as described in the paper.