nm-testing
/

Mixtral-8x7B-Instruct-v0.1-FP8-quantized

compressed_tensors

Model card Files Files and versions Community

Mixtral-8x7B-Instruct-v0.1-FP8-quantized / recipe.yaml

sadkins65's picture

Upload folder using huggingface_hub

9804e70 verified 6 months ago

history blame contribute delete

126 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: [lm_head]
	targets: Linear
	scheme: FP8