RedHatAI
/

Qwen2-VL-72B-Instruct-FP8-dynamic

text-generation-inference

compressed-tensors

Model card Files Files and versions

Qwen2-VL-72B-Instruct-FP8-dynamic / recipe.yaml

mgoin's picture

Upload folder using huggingface_hub

269a11e verified 9 months ago

156 Bytes

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