21 lines
530 B
YAML
21 lines
530 B
YAML
default_stage:
|
|
default_modifiers:
|
|
SmoothQuantModifier:
|
|
smoothing_strength: 0.8
|
|
mappings:
|
|
- !!python/tuple
|
|
- ['re:.*q_proj', 're:.*k_proj', 're:.*v_proj']
|
|
- re:.*input_layernorm
|
|
- !!python/tuple
|
|
- ['re:.*gate_proj', 're:.*up_proj']
|
|
- re:.*post_attention_layernorm
|
|
ignore: []
|
|
GPTQModifier:
|
|
targets: [Linear]
|
|
ignore: [lm_head]
|
|
scheme: W4A16
|
|
block_size: 128
|
|
dampening_frac: 0.01
|
|
actorder: static
|
|
offload_hessians: false
|