BCCard
/

Qwen3-235B-A22B-Thinking-2507-NVFP4A16

compressed-tensors

Model card Files Files and versions

Qwen3-235B-A22B-Thinking-2507-NVFP4A16 / recipe.yaml

sh2orc's picture

Upload folder using huggingface_hub

4a36662 verified 5 days ago

history blame contribute delete

151 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head, 're:.*mlp.gate$']
	scheme: NVFP4A16