JKCHSTR
/

llama-joycaption-alpha-two-hf-llava-FP8-Dynamic

Image-Text-to-Text

compressed-tensors

Model card Files Files and versions Community

llama-joycaption-alpha-two-hf-llava-FP8-Dynamic / recipe.yaml

JKCHSTR's picture

Model upload

e7f756a verified 4 months ago

history blame contribute delete

200 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: ['re:.lm_head', 're:multi_modal_projector.', 're:vision_tower.*']
	targets: [Linear]
	scheme: FP8_DYNAMIC