File size: 672 Bytes
dc07f24 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 | quant_stage:
quant_modifiers:
QuantizationModifier:
config_groups:
group_0:
targets: [Linear]
weights:
num_bits: 8
type: !!python/object/apply:compressed_tensors.quantization.quant_args.QuantizationType [
int]
symmetric: true
group_size: null
strategy: channel
block_structure: null
dynamic: false
actorder: null
observer: minmax
observer_kwargs: {}
input_activations: null
output_activations: null
format: null
targets: [Linear]
ignore: [lm_head, visual]
|