justinjja
/

Qwen3-235B-A22B-INT4-W4A16

Text Generation

compressed-tensors

Model card Files Files and versions Community

Qwen3-235B-A22B-INT4-W4A16 / recipe.yaml

justinjja's picture

Upload folder using huggingface_hub

38872fe verified 8 days ago

history blame contribute delete

151 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	ignore: [lm_head, 're:.*\.mlp\.gate$']
	targets: [Linear]
	scheme: W4A16