RedHatAI
/

Llama-3.2-11B-Vision-Instruct-quantized.w4a16

Image-Text-to-Text

text-generation-inference

compressed-tensors

Model card Files Files and versions Community

Llama-3.2-11B-Vision-Instruct-quantized.w4a16

File size: 178 Bytes

231b020

DEFAULT_stage:
  DEFAULT_modifiers:
    GPTQModifier:
      scheme: W4A16
      targets: Linear
      ignore: ['re:.*lm_head', 're:multi_modal_projector.*', 're:vision_model.*']