ramblingpolymath
/

Qwen3-30B-A3B-Thinking-2507-W4A16

Text Generation

compressed-tensors

Model card Files Files and versions Community

Qwen3-30B-A3B-Thinking-2507-W4A16 / recipe.yaml

ramblingpolymath's picture

ramblingpolymath

Upload folder using huggingface_hub

f94dbaf verified 11 days ago

history blame contribute delete

167 Bytes

	default_stage:
	default_modifiers:
	GPTQModifier:
	targets: [Linear]
	ignore: [lm_head, 're:.*mlp.gate$']
	scheme: W4A16
	dampening_frac: 0.01