inference-optimization
/

sarvam-30b-NVFP4

Text Generation

8-bit precision

compressed-tensors

Model card Files Files and versions

sarvam-30b-NVFP4 / recipe.yaml

krishnateja95's picture

Upload folder using huggingface_hub

db39ecb verified about 1 month ago

history blame contribute delete

170 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: NVFP4
	bypass_divisibility_checks: false