noneUsername
/

Replete-LLM-V2.5-Qwen-14b-W8A8-Dynamic-Per-Token

8-bit precision

Model card Files Files and versions Community

Replete-LLM-V2.5-Qwen-14b-W8A8-Dynamic-Per-Token / recipe.yaml

noneUsername's picture

Upload folder using huggingface_hub

d675ee8 verified 14 days ago

171 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.85}
	GPTQModifier:
	targets: Linear
	ignore: [lm_head]
	scheme: W8A8