neuralmagic
/

starcoder2-7b-quantized.w8a8

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

starcoder2-7b-quantized.w8a8 / recipe.yaml

alexmarques's picture

Upload folder using huggingface_hub

d9a8318 verified 1 day ago

history blame contribute delete

173 Bytes

	quant_stage:
	quant_modifiers:
	GPTQModifier:
	sequential_update: false
	dampening_frac: 0.01
	ignore: [lm_head]
	scheme: W8A8
	targets: Linear