nm-testing
/

Qwen2-VL-72B-Instruct-quantized.w4a16

Shubhra Pandit

Upload model files

7a76119 22 days ago

183 Bytes

	DEFAULT_stage:
	DEFAULT_modifiers:
	GPTQModifier:
	sequential_targets: [Qwen2VLDecoderLayer]
	scheme: W4A16
	targets: Linear
	ignore: [lm_head, 're:visual.*']