Files
ModelHub XC 8dcdeaee87 初始化项目,由ModelHub XC社区提供模型
Model: neuralmagic/Llama-2-7b-chat-quantized.w8a8
Source: Original Platform
2026-05-22 08:32:12 +08:00

12 lines
378 B
YAML

quant_stage:
quant_modifiers:
GPTQModifier:
sequential_update: false
dampening_frac: 1
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}