larryvrh
/

Qwen2.5-7B-Instruct-FP8

8-bit precision

Model card Files Files and versions Community

Qwen2.5-7B-Instruct-FP8 / recipe.yaml

larryvrh's picture

Upload folder using huggingface_hub

1e765fd verified 11 days ago

history blame contribute delete

134 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: [lm_head]
	targets: Linear
	scheme: FP8_DYNAMIC