File size: 1,523 Bytes
83be539 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 |
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
format: null
targets: [Linear]
ignore: [model.embed_tokens, 're:.*input_layernorm$', 're:.*linear_attn.*', 're:.*norm.*',
're:.*RMSNorm.*', 're:.*rotary.*', 're:.*shared_expert.*', 're:.*shared_expert_gate$',
're:.*mlp[.]gate$', 're:.*router.*', 're:.*post_attention_layernorm$', 're:.*self_attn.*',
're:mtp.*', lm_head]
mappings:
- smooth_layer: re:.*input_layernorm$
balance_layers: ['re:.*self_attn[.]q_proj$', 're:.*self_attn[.]k_proj$', 're:.*self_attn[.]v_proj$',
're:.*linear_attn[.]in_proj_qkvz$', 're:.*linear_attn[.]in_proj_ba$']
- smooth_layer: re:.*self_attn[.]v_proj$
balance_layers: ['re:.*self_attn[.]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$']
- smooth_layer: re:.*linear_attn[.]norm$
balance_layers: ['re:.*linear_attn[.]out_proj$']
duo_scaling: true
|