neuralmagic
/

starcoder2-15b-quantized.w8a8

Text Generation

text-generation-inference

Inference Endpoints

8-bit precision

Model card Files Files and versions Community

starcoder2-15b-quantized.w8a8

File size: 173 Bytes

quant_stage:
  quant_modifiers:
    GPTQModifier:
      sequential_update: false
      dampening_frac: 0.01
      ignore: [lm_head]
      scheme: W8A8
      targets: Linear