neuralmagic
/

Qwen2.5-3B-quantized.w8a16

Text Generation

compressed-tensors

Model card Files Files and versions Community

Qwen2.5-3B-quantized.w8a16 / recipe.yaml

alexmarques's picture

Upload folder using huggingface_hub

8d33e5d verified 4 months ago

history blame contribute delete

193 Bytes

	quant_stage:
	quant_modifiers:
	GPTQModifier:
	sequential_update: true
	dampening_frac: 0.01
	ignore: [lm_head]
	scheme: W8A16
	targets: Linear
	observer: mse