miike-ai
/

Llama-3.2-1B-Instruct-FP4

compressed-tensors

Model card Files Files and versions

Llama-3.2-1B-Instruct-FP4 / recipe.yaml

miike-ai's picture

Add files using upload-large-folder tool

53f27eb verified over 1 year ago

Raw History Blame Contribute Delete

133 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: NVFP4A16