apolloparty
/

LFM2-700M-NVFP4A16

Text Generation

8-bit precision

compressed-tensors

Model card Files Files and versions Community

LFM2-700M-NVFP4A16 / recipe.yaml

apolloparty's picture

Upload folder using huggingface_hub

fbe71b0 verified 25 days ago

history blame contribute delete

133 Bytes

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