Files
SmolLM-1.7B-Instruct-quanti…/recipe.yaml
ModelHub XC f047a411ff 初始化项目,由ModelHub XC社区提供模型
Model: neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8
Source: Original Platform
2026-06-11 09:28:12 +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