zhiqing
/

Qwen3-1.7B-INT8

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Qwen3-1.7B-INT8 / recipe.yaml

zhiqing's picture

Upload folder using huggingface_hub

9b267f2 verified 3 months ago

history blame contribute delete

170 Bytes

	default_stage:
	default_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.8}
	GPTQModifier:
	scheme: W8A8
	targets: Linear
	ignore: [lm_head]