28 lines
789 B
YAML
28 lines
789 B
YAML
|
quant_stage:
|
||
|
|
quant_modifiers:
|
||
|
|
GPTQModifier:
|
||
|
|
config_groups:
|
||
|
|
group_0:
|
||
|
|
targets: [Linear]
|
||
|
|
weights:
|
||
|
|
num_bits: 4
|
||
|
|
type: int
|
||
|
|
symmetric: false
|
||
|
|
group_size: 64
|
||
|
|
strategy: group
|
||
|
|
block_structure: null
|
||
|
|
dynamic: false
|
||
|
|
actorder: !!python/object/apply:compressed_tensors.quantization.quant_args.ActivationOrdering [
|
||
|
|
static]
|
||
|
|
observer: minmax
|
||
|
|
observer_kwargs: {}
|
||
|
|
input_activations: null
|
||
|
|
output_activations: null
|
||
|
|
format: null
|
||
|
|
targets: [Linear]
|
||
|
|
ignore: [lm_head, 're:.*q_norm', 're:.*k_norm']
|
||
|
|
block_size: 128
|
||
|
|
dampening_frac: 0.01
|
||
|
|
actorder: static
|
||
|
|
offload_hessians: false
|