File size: 254 Bytes
c8a8669 | 1 2 3 4 5 6 7 8 9 | quant_stage:
quant_modifiers:
GPTQModifier:
ignore: [lm_head, 're:.*mlp.gate$']
config_groups:
group_0:
weights: {num_bits: 8, type: int, symmetric: true, strategy: channel, dynamic: false}
targets: [Linear]
|