Files
starcoder2-7b-quantized.w8a8/recipe.yaml
ModelHub XC 58ebf3a379 初始化项目,由ModelHub XC社区提供模型
Model: neuralmagic/starcoder2-7b-quantized.w8a8
Source: Original Platform
2026-09-03 20:26:00 +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