File size: 1,121 Bytes
f58e71f dd32890 f58e71f dd32890 f58e71f dd32890 |
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 |
quant_stage:
quant_modifiers:
AWQModifier:
config_groups:
group_0:
targets: [Linear]
weights:
num_bits: 4
type: int
symmetric: true
group_size: 32
strategy: group
block_structure: null
dynamic: false
actorder: null
observer: mse
observer_kwargs: {}
input_activations: null
output_activations: null
format: null
targets: [Linear]
ignore: [lm_head, model.embed_tokens, 're:.*input_layernorm$', 're:.*post_attention_layernorm$',
model.norm, 're:.*mlp.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:.*mlp.experts.*.gate_proj$', 're:.*mlp.experts.*.up_proj$']
- smooth_layer: re:.*up_proj$
balance_layers: ['re:.*down_proj$']
duo_scaling: true
|