Files
Qwen2.5-VL-3B-Instruct-quan…/recipe.yaml
ModelHub XC f9e5ed2c1d 初始化项目,由ModelHub XC社区提供模型
Model: RedHatAI/Qwen2.5-VL-3B-Instruct-quantized.w4a16
Source: Original Platform
2026-10-06 17:32:13 +08:00

13 lines
423 B
YAML

DEFAULT_stage:
DEFAULT_modifiers:
GPTQModifier:
sequential_targets: [Qwen2_5_VLDecoderLayer]
dampening_frac: 0.01
config_groups:
config_group:
targets: [Linear]
weights: {num_bits: 4, type: int, symmetric: true, group_size: 128, strategy: group,
dynamic: false, actorder: weight, observer: minmax}
targets: Linear
ignore: [lm_head, 're:visual.*']