espressor
/

google.gemma-2-2b-it_W4A16

Text Generation

text-generation-inference

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

google.gemma-2-2b-it_W4A16 / recipe.yaml

xzyao's picture

Upload folder using huggingface_hub

c900ba1 verified 15 days ago

history blame contribute delete

120 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	GPTQModifier:
	targets: Linear
	ignore: [lm_head]
	scheme: W4A16