leon-se
/

Qwen2.5-VL-32B-Instruct-FP8-Dynamic

compressed-tensors

Model card Files Files and versions

Qwen2.5-VL-32B-Instruct-FP8-Dynamic / recipe.yaml

leon-se's picture

Upload folder using huggingface_hub

8beb540 verified 4 months ago

158 Bytes

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