gmonair
/

Qwen2.5-Math-1.5B-Instruct-W8A8-Dynamic-Per-Token

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Qwen2.5-Math-1.5B-Instruct-W8A8-Dynamic-Per-Token / recipe.yaml

gmonair's picture

Upload folder using huggingface_hub

31abdcd verified 3 months ago

170 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.8}
	GPTQModifier:
	targets: Linear
	ignore: [lm_head]
	scheme: W8A8