Files
ModelHub XC 0404fc02dd 初始化项目,由ModelHub XC社区提供模型
Model: nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2
Source: Original Platform
2026-05-02 04:48:02 +08:00

11 lines
354 B
YAML

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