Model Tag vllm is confusing as it refers to serving with vllm package not model type

Models
1

Hi there,
I noticed the tag „vllm“ on models recently and think it might lead to some confusion, as the tag „apparently“ serves to highlight models that can be served using the vllm package (as in „virtual LLM“, I guess).
However this takes away the functional aspect of the model, ie as a „visual LLM“ that can take images or video as input and reason about those input types.
While there‘s a clear task-tag around for both types, maybe a serving-type tag would be beneficial (besides vllm ollama comes to mind)? Let me know what you think.
Best,
M

Examples:
Task-Text-gen, vllm tag:

No-task-tag but vllm tag:

Task-img-Text-gen (+ multimodal, probably the best way w/o a extra serving-tag around):

2

Unless the model author is an HF enthusiast more than he is an author, none of the users are familiar with the HF tag specifications. Based on inadequate official explanations, it is safe to say that the practice is to imitate others and set them up by hand.

Just as HF is looking for users’ opinions. Please try to contribute.
Of those requested, if the changes are easy for HF, some have already been realized!