File size: 775 Bytes
de00f24 4f324b6 e8edc24 4f324b6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 |
pruning_stage:
obcq_modifiers:
SparseGPTModifier:
sparsity: 0.5
sequential_update: true
mask_structure: '2:4'
targets: ['re:model.layers.\d*$']
quant_stage:
quant_modifiers:
QuantizationModifier:
ignore: [lm_head]
config_groups:
group_0:
weights: {num_bits: 8, type: float, strategy: tensor, dynamic: false, symmetric: true}
input_activations: {num_bits: 8, type: float, strategy: tensor, dynamic: true, symmetric: true}
targets: [Linear]
pruning_modifiers:
ConstantPruningModifier:
targets: ['re:.*q_proj.weight', 're:.*k_proj.weight', 're:.*v_proj.weight', 're:.*o_proj.weight',
're:.*gate_proj.weight', 're:.*up_proj.weight', 're:.*down_proj.weight']
start: 0
|