Files
ModelHub XC edc4ba9560 初始化项目,由ModelHub XC社区提供模型
Model: RedHatAI/Qwen2.5-0.5B-quantized.w8a16
Source: Original Platform
2026-10-22 08:28:12 +08:00

10 lines
193 B
YAML

quant_stage:
quant_modifiers:
GPTQModifier:
sequential_update: true
dampening_frac: 0.01
ignore: [lm_head]
scheme: W8A16
targets: Linear
observer: mse