RasmusVeski
/

OLD_llmcompressor_PTQW8A8

Text Generation

text-generation-inference

8-bit precision

compressed-tensors

Model card Files Files and versions Community

OLD_llmcompressor_PTQW8A8 / recipe.yaml

RasmusVeski's picture

Upload Qwen3ForCausalLM

15c8248 verified about 1 month ago

history blame contribute delete

129 Bytes

	default_stage:
	default_modifiers:
	QuantizationModifier:
	ignore: [lm_head]
	targets: [Linear]
	scheme: W8A8