File size: 620 Bytes
246e7b7 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 |
test_stage:
obcq_modifiers:
LogarithmicEqualizationModifier:
mappings:
- - ['re:.*c_attn']
- re:.*ln_1
- - ['re:.*c_fc']
- re:.*ln_2
QuantizationModifier:
ignore: [Dropout, LayerNorm, PytorchGELUTanh]
post_oneshot_calibration: true
scheme_overrides:
Embedding:
input_activations: null
weights: {num_bits: 8, symmetric: false}
SparseGPTModifier:
sparsity: 0.0
block_size: 128
sequential_update: true
quantize: true
percdamp: 0.01
mask_structure: 0:0
targets: ['re:transformer.h.\d*$']
|