Files
Qwen2-0.5B-Instruct-quantiz…/recipe.yaml
ModelHub XC 097514b302 初始化项目,由ModelHub XC社区提供模型
Model: RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8
Source: Original Platform
2026-04-13 11:18:39 +08:00

12 lines
381 B
YAML

quant_stage:
quant_modifiers:
GPTQModifier:
sequential_update: false
dampening_frac: 0.01
ignore: [lm_head]
config_groups:
group_0:
targets: [Linear]
weights: {num_bits: 8, type: int, symmetric: true, strategy: channel}
input_activations: {num_bits: 8, type: int, symmetric: true, dynamic: true, strategy: token}