nm-testing
/

Qwen2-VL-7B-Instruct-FP8-dynamic

Model card Files Files and versions Community

File size: 156 Bytes

53412c5

DEFAULT_stage:
  DEFAULT_modifiers:
    QuantizationModifier:
      ignore: ['re:.*lm_head', 're:visual.*']
      targets: Linear
      scheme: FP8_DYNAMIC