Files
ModelHub XC 9596482c98 初始化项目,由ModelHub XC社区提供模型
Model: RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16
Source: Original Platform
2026-09-26 08:45:13 +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