Files
ModelHub XC 754c15dd2a 初始化项目,由ModelHub XC社区提供模型
Model: RedHatAI/starcoder2-3b-quantized.w8a16
Source: Original Platform
2026-10-23 08:05:12 +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