File size: 353 Bytes
0afbcde
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
quant_stage:
  quant_modifiers:
    GPTQModifier:
      sequential_update: false
      ignore: [lm_head]
      config_groups:
        group_0:
          weights: {num_bits: 8, type: int, symmetric: true, strategy: tensor}
          input_activations: {num_bits: 8, type: int, symmetric: true, dynamic: true, strategy: token}
          targets: [Linear]