Files
gemma-2-2b-it-quantized.w8a8/recipe.yaml
ModelHub XC eea7f4f8dc 初始化项目,由ModelHub XC社区提供模型
Model: RedHatAI/gemma-2-2b-it-quantized.w8a8
Source: Original Platform
2026-04-25 20:19:55 +08:00

9 lines
173 B
YAML

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