neuralmagic
/

gemma-2-9b-it-quantized.w8a8

Text Generation

8-bit precision

compressed-tensors

Model card Files Files and versions Community

gemma-2-9b-it-quantized.w8a8 / recipe.yaml

alexmarques's picture

Upload folder using huggingface_hub

13f2ee0 verified 3 months ago

history blame contribute delete

192 Bytes

	quant_stage:
	quant_modifiers:
	GPTQModifier:
	sequential_update: true
	dampening_frac: 0.01
	ignore: [lm_head]
	scheme: W8A8
	targets: Linear
	observer: mse