HAissa
/

M3_smoothquant096

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions Community

M3_smoothquant096 / recipe.yaml

HAissa's picture

Upload Qwen3ForCausalLM

df77321 verified about 1 month ago

history blame contribute delete

171 Bytes

	default_stage:
	default_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.96}
	GPTQModifier:
	scheme: W4A8
	targets: Linear
	ignore: [lm_head]