tacodevs
/

Behemoth-X-R1-123B-FP8

Text Generation

compressed-tensors

creative-writing

Model card Files Files and versions

Behemoth-X-R1-123B-FP8 / recipe.yaml

tacodevs's picture

Initial upload: FP8 dynamic quantization of Behemoth-X-R1-123B

a70ca0d verified 6 days ago

history blame contribute delete

176 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head]
	scheme: FP8_DYNAMIC
	bypass_divisibility_checks: false