Files
ModelHub XC f005c97068 初始化项目,由ModelHub XC社区提供模型
Model: RedHatAI/gemma-2-9b-it-quantized.w8a16
Source: Original Platform
2026-10-22 17:01:23 +08:00

9 lines
174 B
YAML

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