EmbeddedLLM
/

Qwen2.5-7B-Instruct-FP8-Dynamic

compressed-tensors

Model card Files Files and versions

Qwen2.5-7B-Instruct-FP8-Dynamic / recipe.yaml

tjellm's picture

Upload folder using huggingface_hub

7ee8a82 verified about 2 months ago

history blame contribute delete

136 Bytes

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