nm-testing
/

DeepSeek-Coder-V2-Lite-Instruct-W8A8

8-bit precision

compressed-tensors

Model card Files Files and versions Community

DeepSeek-Coder-V2-Lite-Instruct-W8A8 / recipe.yaml

sadkins65's picture

Upload folder using huggingface_hub

8e637f1 verified 2 months ago

history blame contribute delete

167 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	GPTQModifier:
	sequential_update: true
	targets: Linear
	ignore: [lm_head, 're:.*mlp.gate$']
	scheme: W8A8