28 lines
756 B
YAML
28 lines
756 B
YAML
quant_stage:
|
|
quant_modifiers:
|
|
GPTQModifier:
|
|
config_groups:
|
|
group_0:
|
|
targets: [Linear]
|
|
weights:
|
|
num_bits: 4
|
|
type: int
|
|
symmetric: true
|
|
group_size: 128
|
|
strategy: group
|
|
block_structure: null
|
|
dynamic: false
|
|
actorder: !!python/object/apply:compressed_tensors.quantization.quant_args.ActivationOrdering [
|
|
static]
|
|
observer: mse
|
|
observer_kwargs: {}
|
|
input_activations: null
|
|
output_activations: null
|
|
format: null
|
|
targets: [Linear]
|
|
ignore: [lm_head]
|
|
block_size: 128
|
|
dampening_frac: 0.01
|
|
actorder: static
|
|
offload_hessians: false
|