nm-testing
/

DeepSeek-Coder-V2-Lite-Instruct-FP8

Text Generation

text-generation-inference

Inference Endpoints

compressed-tensors

Model card Files Files and versions Community

DeepSeek-Coder-V2-Lite-Instruct-FP8 / recipe.yaml

mgoin's picture

Upload folder using huggingface_hub

d31fe09 verified 11 days ago

146 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	QuantizationModifier:
	ignore: [lm_head, 're:.*mlp.gate$']
	targets: [Linear]
	scheme: FP8