clejordan
/

MNLP_M3_W4A16llmcompressor_fewsamples

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions

MNLP_M3_W4A16llmcompressor_fewsamples / recipe.yaml

clejordan's picture

Upload Qwen3ForCausalLM

d4b5ee6 verified 11 months ago

history blame contribute delete

171 Bytes

	default_stage:
	default_modifiers:
	SmoothQuantModifier: {smoothing_strength: 0.8}
	GPTQModifier:
	scheme: W4A16
	targets: Linear
	ignore: [lm_head]