MuseGlimmerInference

class rapidtools.models.MuseGlimmerInference(model_id: str | None = None, device: str = 'auto', load_in_4bit: bool = False, temperature: float = 0.4, max_tokens: int = 512, trust_remote_code: bool = False)

Bases: HFVisionInference

Local inference with Meta’s open-weight Muse Glimmer vision-language model.

A thin specialisation of HFVisionInference that defaults to meta-models/Muse-Glimmer-30B and checks that the installed Transformers release knows the muse_glimmer architecture.

Example

>>> from rapidtools.models import MuseGlimmerInference
>>> MuseGlimmerInference.list_available_models()
['meta-models/Muse-Glimmer-30B']
>>> model = MuseGlimmerInference(load_in_4bit=True)
>>> out = model.run_inference('roof.jpg', 'Rate the roof damage 0-5.')
>>> out.text
'3'

Methods

list_available_models	Return the curated catalogue of checkpoints for this family.
run_batch	Process assets sequentially to avoid GPU out-of-memory crashes.
run_inference	Run the model on one prompt and its image(s).
run_inference_batch	Run the model on several prompt/image sets at once (left-padded).
search_hub_models	List the most downloaded image-text-to-text checkpoints on the Hub.