miike-ai
/

qwen-14b-coder-fp8

compressed-tensors

Model card Files Files and versions

qwen-14b-coder-fp8 / recipe.yaml

miike-ai's picture

Add files using upload-large-folder tool

8a4a185 verified 5 months ago

history blame contribute delete

136 Bytes

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