inference-optimization
/

GLM-4.6-NVFP4

8-bit precision

compressed-tensors

Model card Files Files and versions

GLM-4.6-NVFP4 / recipe.yaml

Shubhra Pandit

Upload model files

2c00afe 2 months ago

history blame contribute delete

151 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head, 're:.*\.mlp\.gate$']
	scheme: NVFP4