Files
ModelHub XC fb7410a43a 初始化项目,由ModelHub XC社区提供模型
Model: RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8
Source: Original Platform
2026-05-31 12:10:12 +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