12 lines
429 B
YAML
12 lines
429 B
YAML
quant_stage:
|
|
quant_modifiers:
|
|
QuantizationModifier:
|
|
ignore: [lm_head]
|
|
sequential_targets: [Qwen3DecoderLayer]
|
|
config_groups:
|
|
group0:
|
|
targets: [Linear]
|
|
weights: {num_bits: 8, type: float, symmetric: true, strategy: channel, observer: mse}
|
|
input_activations: {num_bits: 8, type: float, symmetric: true, strategy: token,
|
|
dynamic: true, observer: memoryless}
|