32 lines
1010 B
YAML
32 lines
1010 B
YAML
default_stage:
|
|
default_modifiers:
|
|
AWQModifier:
|
|
config_groups:
|
|
group_0:
|
|
targets: [Linear]
|
|
weights:
|
|
num_bits: 8
|
|
type: int
|
|
symmetric: true
|
|
group_size: 32
|
|
strategy: group
|
|
block_structure: null
|
|
dynamic: false
|
|
actorder: null
|
|
observer: minmax
|
|
observer_kwargs: {}
|
|
input_activations: null
|
|
output_activations: null
|
|
targets: [Linear]
|
|
ignore: [lm_head, 're:.*mlp.gate$', 're:.*mlp.shared_expert_gate$']
|
|
mappings:
|
|
- smooth_layer: re:.*input_layernorm$
|
|
balance_layers: ['re:.*q_proj$', 're:.*k_proj$', 're:.*v_proj$']
|
|
- smooth_layer: re:.*v_proj$
|
|
balance_layers: ['re:.*o_proj$']
|
|
- smooth_layer: re:.*post_attention_layernorm$
|
|
balance_layers: ['re:.*gate_proj$', 're:.*up_proj$']
|
|
- smooth_layer: re:.*up_proj$
|
|
balance_layers: ['re:.*down_proj$']
|
|
duo_scaling: true
|