flozi00
/

QwQ-32B-Preview-FP8

Text Generation

text-generation-inference

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

QwQ-32B-Preview-FP8 / recipe.yaml

flozi00's picture

Upload Qwen2ForCausalLM

5c20dd6 verified 18 days ago

136 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: [lm_head]
	targets: [Linear]
	scheme: FP8_DYNAMIC