File size: 174 Bytes
05acf7e | 1 2 3 4 5 6 7 8 9 | quant_stage:
quant_modifiers:
GPTQModifier:
sequential_update: false
dampening_frac: 0.01
ignore: [lm_head]
scheme: W8A16
targets: Linear
|
05acf7e | 1 2 3 4 5 6 7 8 9 | quant_stage:
quant_modifiers:
GPTQModifier:
sequential_update: false
dampening_frac: 0.01
ignore: [lm_head]
scheme: W8A16
targets: Linear
|