nm-testing
/

TinyLlama-1.1B-Chat-v1.0-FP8-Dynamic-uncompressed

compressed-tensors

Model card Files Files and versions

TinyLlama-1.1B-Chat-v1.0-FP8-Dynamic-uncompressed / recipe.yaml

horheynm's picture

Upload folder using huggingface_hub

490ff06 verified 8 months ago

history blame contribute delete

136 Bytes

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