12 lines
352 B
YAML
12 lines
352 B
YAML
quant_stage:
|
|
quant_modifiers:
|
|
GPTQModifier:
|
|
ignore: [lm_head]
|
|
sequential_targets: [Qwen3DecoderLayer]
|
|
dampening_frac: 0.01
|
|
config_groups:
|
|
group0:
|
|
targets: [Linear]
|
|
weights: {num_bits: 4, type: int, strategy: group, group_size: 64, symmetric: false,
|
|
actorder: weight, observer: mse}
|