Files
ModelHub XC c429e50ba7 初始化项目,由ModelHub XC社区提供模型
Model: neuralmagic/gemma-2-9b-it-quantized.w8a8
Source: Original Platform
2026-09-09 18:38:12 +08:00

10 lines
192 B
YAML

quant_stage:
quant_modifiers:
GPTQModifier:
sequential_update: true
dampening_frac: 0.01
ignore: [lm_head]
scheme: W8A8
targets: Linear
observer: mse