JPishikawa
/

Llama-3.3-Swallow-70B-Instruct-v0.4-FP8-Dynamic

Text Generation

text-generation-inference

compressed-tensors

Model card Files Files and versions Community

Llama-3.3-Swallow-70B-Instruct-v0.4-FP8-Dynamic / recipe.yaml

JPishikawa's picture

Upload folder using huggingface_hub

bb16d71 verified about 2 months ago

history blame contribute delete

136 Bytes

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