File size: 1,369 Bytes
b567e5d | 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 40 41 42 43 44 45 46 47 48 49 50 | quant_stage:
quant_modifiers:
SmoothQuantModifier:
smoothing_strength: 0.8
mappings:
- - ['re:.*q_proj', 're:.*k_proj', 're:.*v_proj']
- re:.*input_layernorm
- - ['re:.*gate_proj', 're:.*up_proj']
- re:.*post_attention_layernorm
ignore: []
algorithm: smoothquant
GPTQModifier:
config_groups:
group_0:
targets: [Linear]
weights:
num_bits: 8
type: int
symmetric: true
group_size: null
strategy: channel
block_structure: null
dynamic: false
actorder: null
scale_dtype: null
zp_dtype: null
observer: memoryless_minmax
observer_kwargs: {}
input_activations:
num_bits: 8
type: int
symmetric: false
group_size: null
strategy: token
block_structure: null
dynamic: true
actorder: null
scale_dtype: null
zp_dtype: torch.int8
observer: null
observer_kwargs: {}
output_activations: null
format: null
targets: [Linear]
ignore: [lm_head]
bypass_divisibility_checks: false
block_size: 128
dampening_frac: 0.01
offload_hessians: false
|