22 lines
724 B
YAML
22 lines
724 B
YAML
|
quant_stage:
|
||
|
|
quant_modifiers:
|
||
|
|
SmoothQuantModifier:
|
||
|
|
smoothing_strength: 0.7
|
||
|
|
mappings:
|
||
|
|
- - ['re:.*q_proj', 're:.*k_proj', 're:.*v_proj']
|
||
|
|
- re:.*input_layernorm
|
||
|
|
- - ['re:.*gate_proj', 're:.*up_proj']
|
||
|
|
- re:.*post_attention_layernorm
|
||
|
|
- - ['re:.*down_proj']
|
||
|
|
- re:.*up_proj
|
||
|
|
GPTQModifier:
|
||
|
|
sequential_update: true
|
||
|
|
dampening_frac: 0.01
|
||
|
|
ignore: [lm_head]
|
||
|
|
config_groups:
|
||
|
|
group_0:
|
||
|
|
targets: [Linear]
|
||
|
|
weights: {num_bits: 8, type: int, symmetric: true, strategy: channel, observer: mse}
|
||
|
|
input_activations: {num_bits: 8, type: int, symmetric: true, strategy: token, dynamic: true,
|
||
|
|
observer: memoryless}
|