neuralmagic
/

gemma-2-2b-it-quantized.w8a16

Text Generation

compressed-tensors

Model card Files Files and versions Community

gemma-2-2b-it-quantized.w8a16

File size: 174 Bytes

72f3a1e

quant_stage:
  quant_modifiers:
    GPTQModifier:
      sequential_update: false
      dampening_frac: 0.01
      ignore: [lm_head]
      scheme: W8A16
      targets: Linear