GadflyII
/

Qwen3-Coder-Next-NVFP4

Text Generation

Mixture of Experts

compressed-tensors

Model card Files Files and versions

Qwen3-Coder-Next-NVFP4 / recipe.yaml

GadflyII's picture

Upload folder using huggingface_hub

162c8fd verified 3 months ago

history blame contribute delete

202 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	targets: [Linear]
	ignore: [lm_head, 're:.mlp.gate$', 're:.mlp.shared_expert_gate$', 're:.linear_attn.']
	scheme: NVFP4