nm-testing
/

Qwen2.5-Coder-32B-Instruct-FP8-dynamic

compressed-tensors

Model card Files Files and versions

Qwen2.5-Coder-32B-Instruct-FP8-dynamic / recipe.yaml

mgoin's picture

Upload folder using huggingface_hub

9f709be verified 9 months ago

history blame contribute delete

141 Bytes

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