BCCard
/

Qwen2.5-VL-72B-Instruct-FP8-Dynamic

text-generation-inference

compressed-tensors

Model card Files Files and versions

Qwen2.5-VL-72B-Instruct-FP8-Dynamic / recipe.yaml

sh2orc's picture

Upload folder using huggingface_hub

2f0180d verified 4 months ago

151 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	ignore: [lm_head, 're:visual.*']
	targets: [Linear]
	scheme: FP8_DYNAMIC